Back to skill

Security audit

ia-code-review

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign with medium confidence: most checks are acceptable, while a scope mismatch and one automatic-fix concern remain, and one referenced file was only partly analyzed.

The verdict is benign, but confidence is medium and analysis was partial: 21 of 22 components were fully scanned, with one reference only partly inspected due to a parser limit. Before installing, consider whether you are comfortable with the reported ability to apply some fixes without approval and the possible mismatch between the stated review purpose and evaluation operations.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
Findings (34)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied commands invoke evaluation and diagnostic operations on the named skill; they do not visibly perform the declared code-review workflow. As supplied, this is a materially different operational purpose, not merely an implementation detail within a review. The distiller implementation is not shown, so additional behavior or resource access cannot be established.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
equences. Extended examples and anti-patterns live in [review-traps-catalog.md](./references/review-traps-catalog.md); load the relevant topics when a claim dep

Credential Access

High
Category
Privilege Escalation
Confidence
90% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/external-review-subprocess.md (reported line 112)May include surrounding context.

md
- SSH private keys: `**/.ssh/**`, `id_rsa`, `id_dsa`, `id_ecdsa`, `id_ed25519`,
  `id_ecdsa_sk`, `id_ed25519_sk`, `id_xmss`, and any extensionless name ending
  in `_rsa` or `_ed25519`
- `.netrc`, `.npmrc`, `.pypirc`, `.dockercfg`, `.pgpass`, `.git-credentials`
- a file named exactly `credentials` (the AWS and gcloud CLI convention)
- Claude Code's exact basenames `.credentials.json` and `.claude.json` at any
  path depth; these can contain sign-in tokens, saved API keys, or MCP server secrets

Credential Access

High
Category
Privilege Escalation
Confidence
80% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/external-review-subprocess.md (reported line 112)May include surrounding context.

md
- SSH private keys: `**/.ssh/**`, `id_rsa`, `id_dsa`, `id_ecdsa`, `id_ed25519`,
  `id_ecdsa_sk`, `id_ed25519_sk`, `id_xmss`, and any extensionless name ending
  in `_rsa` or `_ed25519`
- `.netrc`, `.npmrc`, `.pypirc`, `.dockercfg`, `.pgpass`, `.git-credentials`
- a file named exactly `credentials` (the AWS and gcloud CLI convention)
- Claude Code's exact basenames `.credentials.json` and `.claude.json` at any
  path depth; these can contain sign-in tokens, saved API keys, or MCP server secrets

Credential Access

High
Category
Privilege Escalation
Confidence
80% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/scope-resolution.md (reported line 179)May include surrounding context.

md
oversized or unreadable selected file; mark it failed.

**A credential-bearing path is not excluded here.** This ledger governs local
review, and a tracked `.env`, key, or `.netrc` is precisely where a
committed-secret finding lives; dropping it from `selected` would make that
class unreviewable. Keep the path selected, review it, and report any finding
under the secret-redaction rule in

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/external-review-subprocess.md (reported line 112)May include surrounding context.

md
- SSH private keys: `**/.ssh/**`, `id_rsa`, `id_dsa`, `id_ecdsa`, `id_ed25519`,
  `id_ecdsa_sk`, `id_ed25519_sk`, `id_xmss`, and any extensionless name ending
  in `_rsa` or `_ed25519`
- `.netrc`, `.npmrc`, `.pypirc`, `.dockercfg`, `.pgpass`, `.git-credentials`
- a file named exactly `credentials` (the AWS and gcloud CLI convention)
- Claude Code's exact basenames `.credentials.json` and `.claude.json` at any
  path depth; these can contain sign-in tokens, saved API keys, or MCP server secrets

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/external-review-subprocess.md (reported line 114)May include surrounding context.

md
in `_rsa` or `_ed25519`
- `.netrc`, `.npmrc`, `.pypirc`, `.dockercfg`, `.pgpass`, `.git-credentials`
- a file named exactly `credentials` (the AWS and gcloud CLI convention)
- Claude Code's exact basenames `.credentials.json` and `.claude.json` at any
  path depth; these can contain sign-in tokens, saved API keys, or MCP server secrets

Decide on the path alone; never read the file's content to make the call. For a

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/language-profiles.md (reported line 107)May include surrounding context.

md
- Hardcoded paths that should be variables
- Deploy credentials in unprotected or unmasked CI variables, or deploy jobs allowed on unprotected branches/tags. Protect and mask deploy variables, and restrict deployment to protected refs.
- A remote installer piped directly into a shell interpreter: flag only in jobs or image builds that hold secrets. Use the package manager or a pinned release with a verified checksum; apply the fail-open integrity check in [security-patterns.md](./security-patterns.md).
- TLS verification bypasses in CLI/CI: `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `git -c http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, or `npm config set strict-ssl false`. Supply the intended CA instead, using the tool's CA option such as `--cacert` or `--certificate-authority`.

## GitHub Actions (.github/workflows/*.yml)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/language-profiles.md (reported line 107)May include surrounding context.

md
- Hardcoded paths that should be variables
- Deploy credentials in unprotected or unmasked CI variables, or deploy jobs allowed on unprotected branches/tags. Protect and mask deploy variables, and restrict deployment to protected refs.
- A remote installer piped directly into a shell interpreter: flag only in jobs or image builds that hold secrets. Use the package manager or a pinned release with a verified checksum; apply the fail-open integrity check in [security-patterns.md](./security-patterns.md).
- TLS verification bypasses in CLI/CI: `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `git -c http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, or `npm config set strict-ssl false`. Supply the intended CA instead, using the tool's CA option such as `--cacert` or `--certificate-authority`.

## GitHub Actions (.github/workflows/*.yml)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/language-profiles.md (reported line 107)May include surrounding context.

md
- Hardcoded paths that should be variables
- Deploy credentials in unprotected or unmasked CI variables, or deploy jobs allowed on unprotected branches/tags. Protect and mask deploy variables, and restrict deployment to protected refs.
- A remote installer piped directly into a shell interpreter: flag only in jobs or image builds that hold secrets. Use the package manager or a pinned release with a verified checksum; apply the fail-open integrity check in [security-patterns.md](./security-patterns.md).
- TLS verification bypasses in CLI/CI: `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `git -c http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, or `npm config set strict-ssl false`. Supply the intended CA instead, using the tool's CA option such as `--cacert` or `--certificate-authority`.

## GitHub Actions (.github/workflows/*.yml)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
60% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/language-profiles.md (reported line 107)May include surrounding context.

md
- Hardcoded paths that should be variables
- Deploy credentials in unprotected or unmasked CI variables, or deploy jobs allowed on unprotected branches/tags. Protect and mask deploy variables, and restrict deployment to protected refs.
- A remote installer piped directly into a shell interpreter: flag only in jobs or image builds that hold secrets. Use the package manager or a pinned release with a verified checksum; apply the fail-open integrity check in [security-patterns.md](./security-patterns.md).
- TLS verification bypasses in CLI/CI: `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `git -c http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, or `npm config set strict-ssl false`. Supply the intended CA instead, using the tool's CA option such as `--cacert` or `--certificate-authority`.

## GitHub Actions (.github/workflows/*.yml)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/scope-resolution.md (reported line 21)May include surrounding context.

md
Treat every modified, staged, and untracked file in that output as the user's
work-in-progress, not as clutter to clear. Do **not**, as review setup, run any
of: `git switch` / `git checkout <branch>`, `git reset --hard`, `git clean`,
`git stash` / `git stash -u`, or `gh pr checkout`. Each silently relocates or
destroys uncommitted work.

YARA rule 'agent_skill_destructive_autonomous_actions': Autonomous destructive filesystem, shell history, or repository actions in AI agent skills [agent_skills]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · references/scope-resolution.md (reported line 21)May include surrounding context.

review

A review is read-only on the working tree. Setting up a review must not mutate what the user has in progress. Before any other setup step, run:

text
git status --short --branch -uall

Treat every modified, staged, and untracked file in that output as the user's work-in-progress, not as clutter to clear. Do not, as review setup, run any of: git switch / git checkout <branch>, git reset --hard, git clean, git stash / git stash -u, or gh pr checkout. Each silently relocates or destroys uncommitted work.

Moving untracked work "out of the way" is the same interference, not a safeguard: do not copy or move the user's WIP to /tmp, a backup dir, or any location outside the checkout to "protect" it. Relocating someone's uncommitted work is the same class of harm as stashing it: it leaves the tree in a state the user did not create and cannot predict.

If the target diff genuinely requires a different branch or a clean tree, stop and ask before switching, st

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/security-patterns.md (reported line 125)May include surrounding context.

md
ith a reachable inherited-property gadget (role check, process or template options), not the API name alone | Reject `__proto__`, `constructor`, and `prototype` at every depth, or use `Map`/null-prototype dictionaries throughout the traversal. `JSON.parse` alone creates an own key; unsafe later traversal creates the pollution |

## Command / Argument Injection

| Search for | Vulnerable pattern | Fix |
|-----------|-------------------|-----|
| PHP `exec(`, `system(`, `shell_exec(`, `passthru(`, backticks, `popen(`, `proc_open(` with a string command; Python `os.system(`, `subprocess.*(..., shell=True)`; Node `child_process.exec(`/`execSync(`, `spawn(..., { shell: true })` | A request-derived value inside a shell command string: `;`, `&&`, `$(...)`, backticks, and newlines run attacker commands | Pass an argv array with no shell: `proc_open([...])` (PHP 7.4+), `subprocess.run([...])` without `shell=True`, `execFile`/`spawn` with an argument array. When a shell string is unavoidable, wrap each value in `escapes

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/security-patterns.md (reported line 188)May include surrounding context.

md
| Search for | Vulnerable pattern | Fix |
|-----------|-------------------|-----|
| `Math.random(`, `random.random(`, `mt_rand(` for tokens/secrets/IDs | Predictable value used as a security control | `crypto.randomBytes`, `secrets.token_urlsafe`, `random_bytes` |
| `verify=False`, `rejectUnauthorized: false`, `NODE_TLS_REJECT_UNAUTHORIZED=0`; `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, `npm config set strict-ssl false` | TLS certificate validation disabled in application, CLI, or CI traffic (MITM) | Remove the bypass; configure the correct CA (`--cacert`, `--certificate-authority`, or the client's trust store) |
| ECB mode, static/reused IV or nonce, home-rolled crypto, MD5/SHA1 for integrity | Deterministic ciphertext, reused nonce, forgeable integrity checks | AES-GCM/ChaCha20-Poly1305 with a fresh nonce, audited libraries, HMAC-SHA256+ |
| `sha256`/`hash_file(`/`hashli

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/security-patterns.md (reported line 188)May include surrounding context.

md
| Search for | Vulnerable pattern | Fix |
|-----------|-------------------|-----|
| `Math.random(`, `random.random(`, `mt_rand(` for tokens/secrets/IDs | Predictable value used as a security control | `crypto.randomBytes`, `secrets.token_urlsafe`, `random_bytes` |
| `verify=False`, `rejectUnauthorized: false`, `NODE_TLS_REJECT_UNAUTHORIZED=0`; `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, `npm config set strict-ssl false` | TLS certificate validation disabled in application, CLI, or CI traffic (MITM) | Remove the bypass; configure the correct CA (`--cacert`, `--certificate-authority`, or the client's trust store) |
| ECB mode, static/reused IV or nonce, home-rolled crypto, MD5/SHA1 for integrity | Deterministic ciphertext, reused nonce, forgeable integrity checks | AES-GCM/ChaCha20-Poly1305 with a fresh nonce, audited libraries, HMAC-SHA256+ |
| `sha256`/`hash_file(`/`hashli

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/security-patterns.md (reported line 188)May include surrounding context.

md
| Search for | Vulnerable pattern | Fix |
|-----------|-------------------|-----|
| `Math.random(`, `random.random(`, `mt_rand(` for tokens/secrets/IDs | Predictable value used as a security control | `crypto.randomBytes`, `secrets.token_urlsafe`, `random_bytes` |
| `verify=False`, `rejectUnauthorized: false`, `NODE_TLS_REJECT_UNAUTHORIZED=0`; `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, `npm config set strict-ssl false` | TLS certificate validation disabled in application, CLI, or CI traffic (MITM) | Remove the bypass; configure the correct CA (`--cacert`, `--certificate-authority`, or the client's trust store) |
| ECB mode, static/reused IV or nonce, home-rolled crypto, MD5/SHA1 for integrity | Deterministic ciphertext, reused nonce, forgeable integrity checks | AES-GCM/ChaCha20-Poly1305 with a fresh nonce, audited libraries, HMAC-SHA256+ |
| `sha256`/`hash_file(`/`hashli

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
60% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/security-patterns.md (reported line 188)May include surrounding context.

md
| Search for | Vulnerable pattern | Fix |
|-----------|-------------------|-----|
| `Math.random(`, `random.random(`, `mt_rand(` for tokens/secrets/IDs | Predictable value used as a security control | `crypto.randomBytes`, `secrets.token_urlsafe`, `random_bytes` |
| `verify=False`, `rejectUnauthorized: false`, `NODE_TLS_REJECT_UNAUTHORIZED=0`; `curl -k`/`--insecure`, `wget --no-check-certificate`, `kubectl --insecure-skip-tls-verify`, `http.sslVerify=false`/`GIT_SSL_NO_VERIFY`, `pip --trusted-host`, `npm config set strict-ssl false` | TLS certificate validation disabled in application, CLI, or CI traffic (MITM) | Remove the bypass; configure the correct CA (`--cacert`, `--certificate-authority`, or the client's trust store) |
| ECB mode, static/reused IV or nonce, home-rolled crypto, MD5/SHA1 for integrity | Deterministic ciphertext, reused nonce, forgeable integrity checks | AES-GCM/ChaCha20-Poly1305 with a fresh nonce, audited libraries, HMAC-SHA256+ |
| `sha256`/`hash_file(`/`hashli

Self-Modification

High
Category
Rogue Agent
Confidence
90% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · references/security-patterns.md (reported line 190)May include surrounding context.

md
tion, CLI, or CI traffic (MITM) | Remove the bypass; configure the correct CA (`--cacert`, `--certificate-authority`, or the client's trust store) |
| ECB mode, static/reused IV or nonce, home-rolled crypto, MD5/SHA1 for integrity | Deterministic ciphertext, reused nonce, forgeable integrity checks | AES-GCM/ChaCha20-Poly1305 with a fresh nonce, audited libraries, HMAC-SHA256+ |
| `sha256`/`hash_file(`/`hashlib`/signature or HMAC verify on a downloaded, cached, or uploaded artifact (installers, self-updaters, plugin or dependency fetchers) | Integrity check fails open: a missing or malformed digest counts as a pass, a mismatch is only logged or its return value is ignored, a mismatch falls back to a mirror or backend that skips verification, or a cache hit is used without re-verifying | A missing digest is a failure; route every acquisition path, cache reads included, through one verify-then-use helper that refuses the artifact on mismatch. Authenticate the expected digest through trus

The review skill directs agents to apply some fixes without approval, extending its stated review-and-critique scope into code modification.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The manifest describes producing structured code reviews and critiquing changes, but the safe_auto action explicitly says to apply fixes directly without prompting. Modifying reviewed code is distinct from reporting findings or suggesting patches, and can alter the user's working tree when only a review was requested.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · references/check-categories.md (reported line 38)May include surrounding context.

md
## Performance

- N+1 queries (loop with query per item; use batch/join instead)
- Unbounded collections (arrays/maps without size limits)
- Missing indexes on queried columns

## Adversarial (red-team pass)

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · references/security-patterns.md (reported line 90)May include surrounding context.

md
n: symlink resolution need not canonicalize case, so on a case-insensitive filesystem (default macOS, Windows) `/tmp/Checkout` can fail to match `/tmp/checkout`; a skipped unreadable ancestor or an unchecked symlink target has the same result | Walk the candidate's ancestors and compare each to the root by file identity (Python `os.path.samefile`, or `stat` `dev`+`ino`). Check both the entry's directory and its resolved target's directory, and refuse on any stat or resolve error |
| File upload without size limit | Unrestricted upload = DoS | Set limits in the actual upload parser: Flask `MAX_CONTENT_LENGTH`; Multer `limits.fileSize`, `limits.files`, and `limits.parts`, plus `limits.fieldNestingDepth` (multer 2.2.0+) and `limits.fieldArrayIndexLimit` (multer 2.3.0+), both defaulting to `Infinity`; a field name like `a[4294967294]` builds a sparse array whose length the application pays for when it iterates or serializes `req.body`, and no option bounds it before 2.3.0. Use `express.jso

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/deep-review.md (reported line 87)May include surrounding context.

md
DON'T:
- Take the author's summary at face value. "Refactored X" may hide behavioral changes.
- Accept "this is covered by tests" without checking the test files in the diff.
- Rubber-stamp sections you didn't open. If you didn't read it, you didn't review it.
- Extrapolate from the description when the code contradicts it -- the code wins.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/review-judgment-traps.md (reported line 15)May include surrounding context.

md
- Skipping Stage 1: never review code quality before verifying spec compliance; rubber-stamping without reading is not a review

- Recommending fix patterns without checking currency: verify the pattern is current for the project's framework version; prefer newer built-in alternatives

- Fighting adopted overrides: in diff review, honor a documented bypass only when applicable caller/harness authority explicitly adopts it for that review. A rationale in `CLAUDE.md`, `AGENTS.md`, a threat model or ADR, or an inline comment does not establish that authority by itself. Treat unadopted rationale as evidence to evaluate. Record an adopted override's disposition with both the rationale's location and the caller/harness adoption; do not re-raise the covered issue. If the adopted override lacks rationale, suggest documenting one. An override counts only if it exists at the review's base revision (read it with `git show --no-textconv --no-ext-diff <base>:<file>`, not from the working tree); an

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/review-judgment-traps.md (reported line 21)May include surrounding context.

md
- Calling a change a regression without a baseline read: read the pre-change file (`git show --no-textconv --no-ext-diff <base>:<file>`), not just the hunk; cite the introducing commit when confirmed. A recalled "since commit/issue N" is unverified history: before a commit or PR body names it, run `git log -S'<exact line>' origin/<base> -- <file>` and cite the result, or drop the attribution. The pickaxe skips merge commits unless given `-m`, so by default it misses a line a merge brought back

- Widening/narrowing a key or guard without checking the mirror bug: name one concrete opposite-defect case along the now-ignored axis before accepting the fix

- Pre-classifying own findings as weak: no "INFO only" / "no action required" wording; anchor severity in concrete constants from the code, not hypotheticals