ClawAudit verdict

social-media-title-insight

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

The skill uses package installation and credential access, but it appears to be used legitimately for its stated purpose of analyzing social media post titles.

⚠ 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.

53
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match high

<script> tag in markdown — potential code injection

scripts/data_tool.py · prose · downgraded · <script

Pattern match high

Uses eval() — can execute arbitrary code

scripts/data_tool.py · prose · downgraded · eval(

Pattern match low

Python urllib.request — network access

scripts/data_tool.py · prose · downgraded · urllib.request

Permissions & capabilities

No declared permissions — minimal attack surface.

package_install

Is this flag fair?

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