track-management
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for developer-generated files (spec.md, plan.md, tracks.md) that the agent is expected to process and update, representing a surface for instructions embedded in data.
- Ingestion points: Ingests data from spec.md, plan.md, tracks.md, and metadata.json (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined in the file templates.
- Capability inventory: The skill utilizes file system write operations and /conductor namespace commands.
- Sanitization: No sanitization or validation logic for the content of the markdown files is described.
- [COMMAND_EXECUTION]: The skill documents the use of specific tooling commands (/conductor:new-track and /conductor:revert) for managing the project lifecycle.
Audit Metadata