ClawAudit verdict

gen-coding-specs

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

Generates technical coding specification documents for the current workspace from templates; entirely local file operations with no network calls or credential access.

⚠ 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 (6)

Pattern match critical

Possible hardcoded credential

coding.testing.md · code · password: 'password

Pattern match critical

<script> tag in markdown — potential code injection

coding.vue.md · code · <script

Pattern match high

Pipe to python — executes piped content as Python code

coding.documentation.md · prose · downgraded · | Python

Pattern match high

Dynamic import() — loads module at runtime

coding.performance.md · code · import('

Pattern match medium

Accesses sensitive environment variables

coding.security.md · code · process.env.JWT_SECRET

Pattern match low

Popular HTTP library — network access

prompt.md · prose · downgraded · Axios

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