ClawAudit verdict

jb-rcm-pulse

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

The skill provides daily learning pulses on revenue cycle management, focusing on structured learning and knowledge reinforcement without showing malicious behavior.

⚠ 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.

63
security
70
transparency
70
maintenance

Findings (5)

Pattern match high

Possible hardcoded credential

test_api.py · prose · downgraded · TOKEN = "moltbook_sk_h_WdHz8lcsCi_-tUAgZtMZEAVcg22chm

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

CRCR_CURRICULUM.md · prose · downgraded · you are now

Pattern match low

Popular HTTP library — network access

CRCR_CURRICULUM.md · prose · downgraded · got

Pattern match low

Python urllib.request — network access

post_moltbook.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

post_moltbook.py · prose · downgraded · os.environ.get(

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