review-response
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external sources which creates a surface for indirect prompt injection.
- Ingestion points: Review feedback is received from 'any channel', including 'external contributors' and 'automated tools' as described in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the feedback strings, though they do mandate a restatement phase.
- Capability inventory: The skill allows the agent to modify the codebase ('ACT: Address one item at a time') and use the
gh apitool to post replies to GitHub comments. - Sanitization: There are no instructions for sanitizing or escaping the content of the feedback before it is evaluated by the agent.
Audit Metadata