implement-spec
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill coordinates multiple sub-agents using inputs from external specifications and task trackers, which represent untrusted data sources.
- Ingestion points: The agent reads specifications, task definitions, and issue tracker data to manage the implementation workflow as seen in SKILL.md.
- Boundary markers: The instructions for sub-agents in IMPLEMENTER-PROMPT.md interpolate task data without using strict delimiters or 'ignore' instructions for embedded content.
- Capability inventory: The skill performs Git operations, manages local worktrees, writes status files to the .dev-skills directory, and executes test suites.
- Sanitization: No explicit content validation or sanitization of the input specifications is mentioned.
- [COMMAND_EXECUTION]: The skill manages a development lifecycle that involves environment setup, dependency installation, and running test suites across multiple local worktrees. These actions involve executing shell commands derived from the project's structure and the assigned tasks.
Audit Metadata