build
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various Git commands (
git status,git worktree add,git diff) and runs the "repo's test command." Running repository-defined test commands allows for arbitrary code execution based on the contents of the repository's configuration (e.g.,package.json,Makefile). - [INDIRECT_PROMPT_INJECTION]: The skill processes implementation plans from file paths provided as arguments or found in
${TMPDIR}ordocs/plans/. - Ingestion points: Reads plan files from disk (SKILL.md, Step 1).
- Boundary markers: None identified for plan content parsing.
- Capability inventory: File modification, Git operations, and execution of test commands.
- Sanitization: None identified; the skill directly implements the steps described in the plan.
- [DATA_EXPOSURE]: The skill attempts to read configuration from
~/.agents/models.json. Accessing files within the user's home directory is a sensitive operation that can expose user-specific tool configurations or metadata.
Audit Metadata