implement-afk-agentic
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill creates a secure operational framework for coding tasks by enforcing human-in-the-loop triggers and pre-agreed testing boundaries.
- [COMMAND_EXECUTION]: Git operations are used for branch and commit management, with branch names sanitized from issue titles to prevent common injection vectors.
- [PROMPT_INJECTION]: The skill manages the risk of indirect prompt injection from external ticket data via a mandatory 'Halt rule' and strict ingestion preconditions. Evidence chain: Ingestion points: Issue tracker titles, labels, and ticket bodies. Boundary markers: Mandatory verification of the 'ready-for-agent' label and defined 'Seams under test' section before action. Capability inventory: Git operations, file system access, and execution of internal implementation tools (/tdd, /code-review, /open-pr-agentic). Sanitization: Title-to-branch normalization and a strict requirement to stop and comment when ambiguity or missing facts are encountered.
Audit Metadata