Caveat verdict
agent-harness
shenmeng-agent-harness
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill seems to be an agent harness for managing AI coding assistants, but it uses process execution and has a payment system.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
80
security
80
transparency
70
maintenance
Findings (1)
Pattern match high
Possible hardcoded credential
payment.py · prose · downgraded · API_KEY = "sk_f03aa8f8bbcf79f7aa11c112d904780f22e62add1464e3c41a79600a451eb1d2
Permissions & capabilities
No declared permissions — minimal attack surface.
process_exec Is this flag fair?
Thanks — recorded.