pr-review
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from pull requests, issues, and repository files, which creates an attack surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to gather PR/Issue links, code diffs, snapshots, repository rules, and logs (SKILL.md).
- Boundary markers: No specific delimiters or boundary markers are defined to isolate untrusted data from the agent's instructions.
- Capability inventory: The skill analyzes repository state and files. The instructions include a "Stay read-only unless authorized" directive, suggesting limited modification capability.
- Sanitization: There are no instructions for sanitizing or escaping the external data before it is processed by the agent.
Audit Metadata