map-reduce
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external data (e.g., codebase files) which serves as an ingestion point for untrusted content.
- Ingestion points: Data is read from the filesystem using bash and file tools during the Map phase.
- Capability inventory: The skill utilizes file: write, mcp: task, and bash tools, which allows it to modify the environment based on the analysis of ingested data.
- Boundary markers: The orchestration pattern does not define explicit delimiters or instructions to ignore embedded commands within the files being processed.
- Sanitization: There are no instructions for sanitizing or validating external file content before it is interpolated into the agent's context for processing.
Audit Metadata