staff-engineer-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from pull requests.
- Ingestion points: In
SKILL.md, theGather Inputssection specifies that the agent must collect the "PR Description" and "Code Changes" as the primary data for analysis. - Boundary markers: The instructions do not define any boundary markers or instructions to treat the ingested data as untrusted or to ignore instructions embedded within the PR content.
- Capability inventory: The skill itself does not request any tools or scripts that perform dangerous actions like network access or file system modifications, limiting the impact of a potential injection.
- Sanitization: There are no defined procedures for the agent to sanitize or validate the content of the pull request data before evaluating it.
Audit Metadata