biome-code-review
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files and pull requests, creating a surface for indirect prompt injection.\n- Ingestion points: SKILL.md instructs the agent to read PR titles, bodies, and diffs via
gh pr viewandgh pr diff, and read repository files for context.\n- Boundary markers: There are no technical delimiters or specific instructions to ignore embedded prompts in the ingested PR or file data.\n- Capability inventory: The skill permits execution of specific shell commands (git,gh) and file reading.\n- Sanitization: No sanitization of the retrieved external content is specified.
Audit Metadata