inspect-change
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from code diffs and requirements documents, creating an attack surface where malicious instructions could influence the agent's review.
- Ingestion points: The skill ingests data from
git diffoutputs and externalrequirements.mdfiles (SKILL.md, Steps 1 and 2). - Boundary markers: Explicit boundary markers or instructions to treat diff content as untrusted are absent from the dispatch instructions (SKILL.md, Step 4).
- Capability inventory: The skill uses
gitfor read-only repository inspection and dispatches subagents to analyze code (SKILL.md, Step 4). - Sanitization: There is no mention of sanitizing or escaping the content of the diffs or requirements before processing (SKILL.md).
Audit Metadata