conductor-status
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project files (e.g.,
product.md,tracks.md,plan.md). While this is a theoretical injection surface, the skill's operations are limited to data extraction, regex-based task counting, and formatting for display. It does not execute commands based on the content of these files, nor does it perform network operations that could facilitate exfiltration. - Ingestion points: Reads from
conductor/product.md,conductor/tracks.md, and track-specific files inconductor/tracks/. - Boundary markers: Output is structured within predefined markdown templates.
- Capability inventory: Limited to file read operations and console output.
- Sanitization: Not explicitly defined, but the risk is minimized by the lack of execution or exfiltration capabilities.
Audit Metadata