track-manager
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific files (tracks.md, spec.md, plan.md, metadata.json) which could be used as a vector for indirect instructions if those files are modified by untrusted actors.
- Ingestion points: The skill reads documentation and status files from the conductor/ directory (SKILL.md).
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are defined for the file processing tasks (SKILL.md).
- Capability inventory: The skill is authorized to perform file read and write operations on the project structure (SKILL.md).
- Sanitization: The instructions do not include steps for sanitizing or validating the text content of the markdown files before ingestion (SKILL.md).
Audit Metadata