ClawAudit verdict

singlefile-output-reference

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Provides a reference catalog of single-file output types (HTML apps, Python CLI, Shell scripts, SQL scripts) with templates and structure requirements; purely informational/reference content with no external calls.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
90
transparency
70
maintenance

Findings (7)

Pattern match critical

Pipe to python — executes piped content as Python code

references/output-catalog.md · code · | python

Pattern match critical

<script> tag in markdown — potential code injection

references/exemplars.md · code · <script>

Pattern match critical

Uses eval() — can execute arbitrary code

references/exemplars.md · code · eval(

Pattern match high

Pipe to bash — executes piped content as shell commands

SKILL.md · prose · downgraded · | Bash

Pattern match high

Uses spawn() — can execute external programs

references/exemplars.md · code · spawn(

Pattern match medium

Opens WebSocket connection

references/output-catalog.md · code · WebSocket

Pattern match low

Python urllib.request — network access

references/structure-requirements.md · prose · downgraded · urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API