ClawAudit verdict

social-media-autopilot

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

Multi-platform social media scheduler with explicit approval workflow preventing auto-publishing without user confirmation; credential use is transparent.

⚠ 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.

40
security
90
transparency
70
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

references/instagram-setup.md · code · TOKEN="your_long_lived_token

Pattern match high

Pipe to python — executes piped content as Python code

scripts/draft-post.sh · prose · downgraded · | python3

Pattern match medium

Social engineering — falsely claims user authorization

SKILL.md · prose · downgraded · the user has configured

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