ClawAudit verdict
user-interview
Usercall API integration for running user interviews; credentials go only to app.usercall.co, straightforward study setup with no unexpected data exfiltration.
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
network_out
Findings (2)
Possible hardcoded credential
SKILL.md ยท prose ยท downgraded ยท API_KEY="your_key_here
Accesses shell history/config
SKILL.md ยท prose ยท downgraded ยท ~/.zshrc
Permissions & capabilities
No declared permissions โ minimal attack surface.
credential_accessnetwork_out Is this flag fair?
Thanks โ recorded.