rail-tdd
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to read and follow external project-level documentation, which could contain instructions that influence agent behavior if those files are sourced from untrusted contributions.
- Ingestion points: The skill explicitly instructs the agent to read
docs/monorail/CONTEXT.mdand files withindocs/monorail/adr/in theSKILL.mdfile. - Boundary markers: No explicit boundary markers or instructions to disregard embedded commands in those files are provided.
- Capability inventory: The skill requires the agent to use shell tools to check file paths and interact with the codebase.
- Sanitization: There is no evidence of sanitization or filtering for the content read from these documentation files.
Audit Metadata