implement
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon externally provided, untrusted data which can influence its behavior.
- Ingestion points: The 'Define' phase explicitly instructs the agent to 'Read the provided context, repository instructions, and relevant code' from the file system.
- Boundary markers: There are no instructions to use delimiters or ignore embedded natural language instructions within the processed files.
- Capability inventory: The skill's primary function involves 'Build' and 'Fix and verify' phases which typically require the agent to write files and execute shell commands for testing and linting.
- Sanitization: The skill lacks any instructions for sanitizing or validating the input from repository-level instruction files before processing.
Audit Metadata