Back to skill

Security audit

Planning with files

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this planning skill suspicious because it reports filesystem safety and scope concerns, and its review of the 34 listed components was only partial.

Consider the suspicious verdict before installing. The main reported risks are silent replacement of existing loop instructions, unsafe selection or modification of project plan files, and hook or summary behavior that may affect agent context. Skillspector inspected 25 of 34 components fully and 9 partially, so the evidence is incomplete; several alerts were also disputed by its reviewer. The scanners do not establish malicious intent.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/phase-status.ps1
Finding

PowerShell writers trust an unvalidated workspace plan pointer

Content
View full analysis

Impact

Unauthorized modification of another project's plan status and creation or modification of external ledger state. The phase writer is constrained to the requested phase/status transformation; this is not unrestricted arbitrary-content execution.

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/check-complete.sh
Finding

Automatic gated Stop writes follow attacker-planted sidecar symlinks

Content
View full analysis

Impact

Destruction of a targeted writable configuration or data file by replacing it with a number. The written bytes are constrained counters, not attacker-chosen executable content.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (41)

Tainted flow: 'ledger_dir' from sys.stdin.read (line 1324, user input) → subprocess.run (code execution)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

External input (network, user) flows to a code execution sink. This enables remote code execution or command injection.

Content

Scanner excerpt · scripts/inject-plan.py (reported line 1413)May include surrounding context.

python
sh = shutil.which("sh")
        if not sh:
            raise RuntimeError("ledger-summary.sh needs a POSIX sh")
        result = subprocess.run(
            [sh, lsum_sh, ledger_dir],
            stdout=subprocess.PIPE,
            stderr=subprocess.DEVNULL,

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 99)May include surrounding context.

md
PowerShell equivalents are `init-session.ps1` and `check-complete.ps1 -Validate -PlanFile path/to/task_plan.md`. A named task may use the initializer's name arg

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 242)May include surrounding context.

md
- `scripts/set-active-plan.sh` — Switch or inspect the active plan pointer (`.planning/.active_plan`). Run with `--list` to show named plans and phase counts, w

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 277)May include surrounding context.

md
`set-active-plan.sh` changes the repository's shared default pointer, so use it for sequential switching. It does not bind concurrent sessions. `PWF_PLAN_ROOT`

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 311)May include surrounding context.

md
The standalone `scripts/skill-hook.sh` reads the host's JSON session identity. UserPromptSubmit emits plain context; PreToolUse and PostToolUse emit the event's

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 409)May include surrounding context.

md
| Progress injection | Raw `tail -20 progress.md` | `ledger-summary.sh` synthesized block | `ledger-summary.sh` synthesized block |

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 464)May include surrounding context.

md
the raw `progress.md` tail injection is replaced by a synthesized summary from `scripts/ledger-summary.sh`. The summary reports tick count, phase complete/total

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 466)May include surrounding context.

md
gress.md` mtime (which moves on any touch). See `scripts/ledger-append.sh` and `scripts/ledger-summary.sh`.

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 510)May include surrounding context.

md
unattended run) used to flow into context every turn. v3 injects a synthesized `ledger-summary.sh` block with no free text from disk instead.

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 466)May include surrounding context.

md
mantic signal) rather than `progress.md` mtime (which moves on any touch). See `scripts/ledger-append.sh` and `scripts/ledger-summary.sh`.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% 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 · scripts/attest-plan.sh (reported line 448)May include surrounding context.

sh
*) lock_type=directory ;;
        esac
    fi
    rm -f "${staging}/probe"
    claim_writer() {
        case "${lock_type}" in
            link) ln "${claim}" "${writer_dir}/" 2>/dev/null ;;

Chaining Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Content

Scanner excerpt · scripts/attest-plan.sh (reported line 479)May include surrounding context.

sh
done
    release_writer() {
        case "${lock_type}" in
            link) [ "${claim}" -ef "${lock_path}" ] && rm -f "${lock_path}" ;;
            directory) rmdir "${lock_path}/${owner}" && rmdir "${lock_path}" ;;
            windows)
                if [ -f "${lock_path}" ] && [ ! -L "${lock_path}" ] &&

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
97% confidence
Finding

The removal itself is bounded, but the immediately preceding 9> redirection opens the predictable project-local .attestation.lock path with truncation and follows symlinks. An attacker able to plant that path can cause attestation to truncate another file writable by the agent; the separate writer lock does not prevent a malicious filesystem entry.

Content

Scanner excerpt · scripts/attest-plan.sh (reported line 583)May include surrounding context.

sh
flock -w 5 9 || true
                mv -f "${tmp_file}" "${attestation_file}"
            ) 9>"${lock_dir}/.attestation.lock" 2>/dev/null || mv_ok=0
            rm -f "${lock_dir}/.attestation.lock" 2>/dev/null
        else
            mv -f "${tmp_file}" "${attestation_file}" 2>/dev/null || mv_ok=0
        fi

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% 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 · scripts/init-session.sh (reported line 201)May include surrounding context.

sh
# (a) reset the gate block counter and drop any stale gate ledger so a prior
    #     run's high block count cannot let the next run stop instantly.
    printf '0\n' > "${_mode_dir}/.stop_blocks"
    rm -f "${_mode_dir}/.gate_last_ledger" 2>/dev/null || true

    # (b) write a fresh 16-hex nonce for delimiter framing.
    gen_nonce > "${_mode_dir}/.nonce"

Code capability 'env' detected in scripts/inject-plan.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Code capability 'network' detected in scripts/session-catchup.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · scripts/session-catchup.py (reported line 835)May include surrounding context.

python
def extract_messages_after(messages: List[Dict[str, Any]], after_line: int) -> List[Dict[str, Any]]:
    """Extract conversation messages after a certain line number."""
    tool_results = collect_claude_tool_results(messages)
    result = []
    for msg in messages:

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.

md
UserPromptSubmit:
    - hooks:
        - type: command
          command: "[ -n \"${CLAUDE_PLUGIN_ROOT:-}\" ] && exit 0; SH=\"${CLAUDE_SKILL_DIR}/scripts/skill-hook.sh\"; [ -f \"$SH\" ] || SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/skill-hook.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/skill-hook.sh\" 2>/dev/null | head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --event=userprompt; exit 0"
  PreToolUse:
    - matcher: "Write|Edit|Bash|Read|Glob|Grep"
      hooks:

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
- matcher: "Write|Edit|Bash|Read|Glob|Grep"
      hooks:
        - type: command
          command: "[ -n \"${CLAUDE_PLUGIN_ROOT:-}\" ] && exit 0; SH=\"${CLAUDE_SKILL_DIR}/scripts/skill-hook.sh\"; [ -f \"$SH\" ] || SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/skill-hook.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/skill-hook.sh\" 2>/dev/null | head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --event=pretool; exit 0"
  PostToolUse:
    - matcher: "Write|Edit"
      hooks:

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
- matcher: "Write|Edit"
      hooks:
        - type: command
          command: "[ -n \"${CLAUDE_PLUGIN_ROOT:-}\" ] && exit 0; SH=\"${CLAUDE_SKILL_DIR}/scripts/skill-hook.sh\"; [ -f \"$SH\" ] || SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/skill-hook.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/skill-hook.sh\" 2>/dev/null | head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --event=posttool; exit 0"
  Stop:
    - hooks:
        - type: command

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
Stop:
    - hooks:
        - type: command
          command: "[ -n \"${CLAUDE_PLUGIN_ROOT:-}\" ] && exit 0; SH=\"${CLAUDE_SKILL_DIR}/scripts/skill-hook.sh\"; [ -f \"$SH\" ] || SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/skill-hook.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/skill-hook.sh\" 2>/dev/null | head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --event=stop; exit 0"
  PreCompact:
    - matcher: "*"
      hooks:

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
- matcher: "*"
      hooks:
        - type: command
          command: "[ -n \"${CLAUDE_PLUGIN_ROOT:-}\" ] && exit 0; SH=\"${CLAUDE_SKILL_DIR}/scripts/skill-hook.sh\"; [ -f \"$SH\" ] || SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/skill-hook.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/skill-hook.sh\" 2>/dev/null | head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --event=precompact; exit 0"
metadata:
  version: "3.29.0"
---

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

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Loop-template installation can overwrite existing host instructions without a warning.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The documented cp commands silently replace existing user-wide or project-specific loop instructions. Following this installation procedure can erase customized safety constraints or workflow controls, with the user-wide destination affecting unrelated projects as well.

Content

No source excerpt is available for this finding.

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
70% confidence
Finding

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 512)May include surrounding context.

md
er injection.** In autonomous and gated mode the raw `progress.md` tail is no longer injected. `progress.md` is not covered by attestation, so any instruction-like text written there (for example a tool output or a fetched page summary appended during an unattended run) used to flow into context every turn. v3 injects a synthesized `ledger-summary.sh` block with no free text from disk instead.
- **Attestation default-on.** Autonomous and gated mode attest the plan at init. Unattended loops amplify any single injection on every tick, so the tamper gate is on from the start, not opt-in. Editing the plan after init requires explicit re-attest.
- **User-private SHA cache.** The hook SHA cache moved from a world-writable `/tmp` path to `$XDG_CACHE_HOME/pwf-sha` (or `~/.cache/pwf-sha`), which removes the shared-tmp poisoning surface. In gated mode the cache is a perf hint only: the gate path always re-hashes so the termination oracle never trusts a stale entry.

| Rule | Why |
|------|-----|