mental
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates a strong security posture by explicitly prohibiting the storage of secrets, credentials, or private keys. It also relies on user-defined policies found in the '.balakit/installed.json' configuration file.\n- [COMMAND_EXECUTION]: To maintain privacy, the skill executes 'git check-ignore' to ensure that the '.mental/' directory is not being tracked by git before it attempts to create any files. It also references 'balakit' via npx as a diagnostic tool for the user.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests data from external repository sources such as commit messages and pull request descriptions.\n
- Ingestion points: SKILL.md (Deriving state from branch info, commits, and open PRs).\n
- Boundary markers: Absent.\n
- Capability inventory: Local file system write access to the '.mental/' directory.\n
- Sanitization: Absent.
Audit Metadata