correct
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external data from the repository's history, which may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Reads recent commits, reverts, review comments, agent instruction files, and code comments to identify mistake patterns (SKILL.md).
- Boundary markers: Absent. There are no instructions to treat the analyzed repository metadata as untrusted or to ignore instructions embedded within those sources.
- Capability inventory: The skill allows for repository-wide architectural changes, file system writes, and the execution of tests and linting commands (SKILL.md).
- Sanitization: Absent. The skill does not specify any sanitization or validation of the repository data before it is processed.
Audit Metadata