ClawAudit verdict
portkey-guardrails
Workspace guardrail hook implementing prompt injection detection, PII redaction, and budget guards running entirely offline without external services — detection patterns like 'Ignore all previous instructions' appear as interception targets, not injections.
⚠ 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 (4)
Prompt injection — tries to override agent instructions
SKILL.md · frontmatter · Ignore all previous instructions
Possible prompt injection — attempts to redefine agent identity
tests/cases.yaml · prose · downgraded · You are now
Base64 encoding/decoding
SKILL.md · prose · downgraded · base64-encode
References agent configuration files
SKILL.md · prose · downgraded · agent-config
Permissions & capabilities
Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.