pocket-grinding
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git logto scan recent commit history for context and a project-specific CLI (pocketto-pi) to log lifecycle events after user approval. These actions are transparent and aligned with the skill's purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes project manifest files and issue comments to gather context. This ingestion is mediated by a structured BDD formulation process and a mandatory human approval step for the generated specification, providing effective oversight for untrusted input.
Audit Metadata