ClawAudit verdict
contract-risk-analyzer
contract-risk-review
This skill analyzes contracts using a user-provided OpenAI-compatible API key and optionally pushes results to Feishu; credential_access refers to the user-provided API key used for its stated purpose, and data sent goes only to user-configured endpoints.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (2)
Possible hardcoded credential
README.md ยท code ยท api_key="your-api-key
Python urllib.request โ network access
scripts/main.py ยท prose ยท downgraded ยท urllib.request
Permissions & capabilities
No declared permissions โ minimal attack surface.
credential_access Is this flag fair?
Thanks โ recorded.