publish-pr
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of code review comments, which could contain malicious instructions.
- Ingestion points: The skill is designed to "analyze, address, or respond to PR comments from code review agents" as described in
SKILL.md. - Boundary markers: There are no specific instructions to treat these comments as untrusted or to use delimiters to prevent instructions within comments from being executed.
- Capability inventory: The skill has the ability to resolve merge conflicts, modify code, push changes to a repository, and launch subagents to process these comments (found in
SKILL.md). - Sanitization: No explicit sanitization or validation of the comment content is mentioned in the instructions.
Audit Metadata