code-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and review code changes (git diffs), which are untrusted external data sources.
- Ingestion points: The agent is directed to inspect staged diffs or branch differences in
SKILL.md. - Boundary markers: The instructions do not define delimiters (e.g., XML tags or triple backticks) or provide warnings to ignore instructions embedded within the code comments or documentation being reviewed.
- Capability inventory: The skill performs architecture and implementation analysis, which involves reading and interpreting untrusted file content.
- Sanitization: There are no instructions to sanitize or escape the content of the code changes before processing them.
Audit Metadata