tdd-orchestrate
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill manages the development lifecycle by directly executing
git addandgit commitcommands during the finalization phase. - [DATA_EXFILTRATION]: The skill includes instructions to create GitHub issues for discovered items outside the current scope; however, it explicitly mandates user confirmation before performing this network operation.
- [SAFE]: The primary function of the skill is organizational orchestration, using environment variables to select between team-based or subagent-based execution modes.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes external code and documentation during planning and review phases.
- Ingestion points: Reads project code and test lists during the 'PLAN' and 'REVIEW' phases in
SKILL.md. - Boundary markers: None explicitly defined in the orchestration instructions to isolate external content.
- Capability inventory: Performs file writes (INIT), command execution (COMMIT), and network interactions (GitHub issue creation).
- Sanitization: No specific sanitization or filtering of external input is mentioned.
Audit Metadata