ClawAudit verdict
prompt-defender
The prompt defender skill seems to be designed for scanning AI prompts for potential risks, with no apparent malicious or deceptive 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.
Findings (3)
Prompt injection — tries to override agent instructions
SKILL.md · prose · downgraded · Ignore all previous instructions
Possible prompt injection — attempts to redefine agent identity
SKILL.md · prose · downgraded · You are now
Base64 encoding/decoding
references/patterns.md · prose · downgraded · Base64-encode
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.