krt-review-herald
Pass
Audited by Gen Agent Trust Hub on May 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted pull request comments and feedback which could contain malicious instructions (Indirect Prompt Injection).
- Ingestion points: Feedback is gathered from PR URLs, pasted comments, or local docs in SKILL.md (Step 1).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions in the ingested feedback.
- Capability inventory: The agent can implement code fixes and group them into commits in SKILL.md (Step 3).
- Sanitization: No evidence of sanitization or validation of the ingested feedback content before processing.
Audit Metadata