track-management
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data that could be used to influence agent behavior through malicious instructions embedded in project files or user input.
- Ingestion points: User requirements gathered via interactive Q&A; existing
spec.md,plan.md, andtracks.mdfiles (referenced inreferences/details.md). - Boundary markers: None identified. There are no instructions to use delimiters or ignore embedded instructions within the project files.
- Capability inventory: The skill has the ability to modify the file system (creating/updating markdown and JSON files) and execute specific commands like
/conductor:new-trackand/conductor:revert(referenced inreferences/details.md). - Sanitization: None identified. The documentation does not specify any validation, escaping, or filtering of the content ingested from external project files.
Audit Metadata