orchestrator

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several CLI tools including git, npm, just, and a custom bd tool for task management. These are used within the context of a standard software development workflow for committing code, running tests, and managing issue states.
  • [PROMPT_INJECTION]: While the skill involves complex multi-agent prompting and processes external data (codebase files and subagent outputs), it does so using structured templates and boundary markers. This reduces the risk of indirect prompt injection, though a theoretical surface exists for data processed at runtime. There are no patterns suggesting attempts to bypass safety filters or ignore system instructions.
  • [REMOTE_CODE_EXECUTION]: The skill references running quality gates via npm run check and just check. These execute scripts defined in the local repository's configuration files, which is expected behavior for an agent performing development tasks.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data transmission was found. Network operations are limited to standard git commands (e.g., git push) for repository management.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:50 PM