Back to skill

Security audit

Miao Vision

Security checks for vulnerabilities and agentic risk

Overview

The skill’s capabilities fit its stated purpose, with explicit consent controls and a limited, recoverable export-installer defect.

Review dependency versions before approving installation, especially the optional unpinned npx route. Before export setup, back up any existing ~/.miao-vision/playwright contents: setup may move that directory to a timestamped backup. Optional media sends the confirmed prompt and selected images to external providers and incurs charges. Installed tools and caches remain after plugin removal. Bundled files were inspected; downloaded dependencies were not audited.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (18)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied command modifies persistent local memory by forgetting a specific setting. The description does not disclose memory-management or preference-deletion behavior, and this standalone destructive operation is not shown to be a supporting step in artifact creation, review, export, or validation. The --confirm flag explicitly confirms the operation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding

The command explicitly targets an outcome-memory store rather than a generated artifact or report specification. Applying a memory proposal is an additional state-changing capability not described in the declared purpose. The chunk does not establish unrelated network access or data exfiltration.

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 84)May include surrounding context.

md
After choosing the workflow, run `node scripts/check-miao-viz.mjs --print-path`.

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 96)May include surrounding context.

md
`node scripts/setup-export.mjs --host <host>` as a read-only check. In Pi use

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/article.md (reported line 78)May include surrounding context.

md
| Milestones | `timeline-path` | At least 3 milestones |
| Shared-criteria comparison | `concept-contrast` | Include dimension keys beyond `label` and `text` |
| Meaningful composition | `part-to-whole` | Values form a real whole |
| Before/after state | `before-after` | Clear state boundary |
| Four quadrants | `tradeoff-matrix` | Exactly 4 suitable items |
| Ranking | `ranked-list-chart` | At least 3 ranked items |
| Architecture or dependency flow | `system-diagram` | Explicit `nodes` and `edges` |

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · install/README.md (reported line 26)May include surrounding context.

md
its absolute path. A compatible CLI is accepted even when its version differs
from the recommendation. If missing or incompatible, approve the bundled
installer, which runs `npm install -g @miao-vision/cli` at the fixed recommended
version. It does not use sudo or change shell configuration. Old binaries in
`~/.miao-vision/bin` remain untouched and are no longer selected automatically.

PNG/PDF export requires Playwright and matching Chromium. Run

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · install/claude.md (reported line 25)May include surrounding context.

md
its absolute path. A compatible CLI is accepted even when its version differs
from the recommendation. If missing or incompatible, approve the bundled
installer, which runs `npm install -g @miao-vision/cli` at the fixed recommended
version. It does not use sudo or change shell configuration. Old binaries in
`~/.miao-vision/bin` remain untouched and are no longer selected automatically.

PNG/PDF export requires Playwright and matching Chromium. Run

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · install/codex.md (reported line 21)May include surrounding context.

md
its absolute path. A compatible CLI is accepted even when its version differs
from the recommendation. If missing or incompatible, approve the bundled
installer, which runs `npm install -g @miao-vision/cli` at the fixed recommended
version. It does not use sudo or change shell configuration. Old binaries in
`~/.miao-vision/bin` remain untouched and are no longer selected automatically.

PNG/PDF export requires Playwright and matching Chromium. Run

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · install/openclaw.md (reported line 30)May include surrounding context.

md
its absolute path. A compatible CLI is accepted even when its version differs
from the recommendation. If missing or incompatible, approve the bundled
installer, which runs `npm install -g @miao-vision/cli` at the fixed recommended
version. It does not use sudo or change shell configuration. Old binaries in
`~/.miao-vision/bin` remain untouched and are no longer selected automatically.

PNG/PDF export requires Playwright and matching Chromium. Run

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/install-miao-viz.sh (reported line 6)May include surrounding context.

sh
SCRIPT_DIR=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
VERSION=$(node -e 'process.stdout.write(require(process.argv[1]).recommendedCliVersion)' "$SCRIPT_DIR/../cli-compatibility.json")
if ! npm install -g "@miao-vision/cli@$VERSION"; then
  echo 'Global npm installation failed. Check your npm prefix permissions or use a user-managed Node installation; no sudo was attempted.' >&2
  exit 1
fi
node "$SCRIPT_DIR/check-miao-viz.mjs" --require-recommended --print-path

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

Although this is an installer rather than an MCP server, unversioned npx skills can download and execute a changing npm package with the user's privileges. A compromised release could access local files or alter globally installed agent skills, and --yes suppresses confirmation within the installation flow.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The compatibility installation command executes an unpinned npm package through npx, even though the finding incorrectly labels it an MCP server. A malicious or compromised future release could execute with the user's filesystem access and modify globally installed agent skills.

Content

No source excerpt is available for this finding.

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 · install/pi.md (reported line 14)May include surrounding context.

md
scoped revision, or export a selected version.

The package checks for the CLI version pinned by `cli-compatibility.json`. It
does not download or upgrade the CLI without approval. The Review Viewer binds
only to `127.0.0.1`; its URL is not a public sharing URL.

## Global CLI and exports

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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/media-setup.md (reported line 13)May include surrounding context.

md
4. Ask them to restart or re-enter the Agent environment so it inherits the variable.
5. Verify with `node scripts/check-ai-media.mjs image` or `video`. Do not use a paid generation request as a configuration test.

Never ask the user to paste the Key. Do not read, print, copy, persist, or pass its value in command arguments. Do not write it to the repository or a repository `.env`. Supplier-direct keys are not part of the supported first release.

## Price and Data Notice

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/outcome-brief.md (reported line 62)May include surrounding context.

md
| `nextAction` | Required behavior |
|---|---|
| `instantiate` | Instantiate the Spec without asking another question. |
| `confirm` | Summarize the form, target, consequential assumptions, and safety warning; obtain confirmation before using `--confirm-plan`. |
| `clarify` | Ask exactly `clarification.question`, using its options. Update the Draft Brief from the answer and rerun `artifact plan`; do not patch the Plan. |
| `stop` | Explain the first selection reason and stop; do not guess another workflow. |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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/report.md (reported line 310)May include surrounding context.

md
listed reasons before sharing. `blocked` must not be delivered. Do not regenerate business meaning
from `changes.json` when a period outcome brief exists.

Generate one client report per update. Do not ask the user to choose a client, operator, or manager
edition. Keep the readable body client-facing; evidence, methodology, data-quality details,
anomalies, and review reasons belong in the collapsed diagnostics appendix. Only expose those
details separately when the user requests diagnostics.

The installer replaces an existing shared installation without checking that it is empty, contradicting its preservation comment.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

When staging is used, the installer renames any existing shared directory without verifying that it is empty or unchanged since dependency resolution. This can displace unrelated or concurrently created contents and replace the active installation despite the stated preservation boundary; retaining a backup reduces permanent data-loss risk but does not prevent disruption.

Content

No source excerpt is available for this finding.