conductor-manage

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs file system operations including directory creation, moving, and deletion. Evidence: resources/implementation-playbook.md specifies the use of mkdir -p, mv, and rm -rf for track management. Destructive operations require explicit user confirmation (e.g., typing 'DELETE') as a safety barrier.
  • [PROMPT_INJECTION]: The skill handles untrusted data from the file system used in command construction, presenting an indirect injection surface. 1. Ingestion points: Track directory names within conductor/tracks/ and metadata fields in metadata.json. 2. Boundary markers: Absent. 3. Capability inventory: File system modification (mv, rm -rf) and git operations. 4. Sanitization: The skill mandates that track IDs follow a specific pattern ({shortname}_{YYYYMMDD}), which provides protection against path traversal and command injection by restricting the input structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 02:38 PM
Security Audit — agent-trust-hub — conductor-manage