correct
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to process data from potentially untrusted sources such as recent commits, reverts, and review comments to identify and fix mistakes.
- Ingestion points: Reads recent commits, reverts, review comments, and agent instruction files (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or warnings for the agent to ignore instructions embedded within the data being analyzed.
- Capability inventory: The skill allows the agent to modify repository structure, types, lints, tests, and documentation, and to perform commits (SKILL.md).
- Sanitization: No sanitization or validation of the external content is specified before the agent acts on it.
Audit Metadata