tdd-repair
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a user-provided test command and allows the repair agent to use the Bash tool for code modifications.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes source code and tests from an external repository.
- Ingestion points: Target repository files and test files.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are documented for the AI prompt.
- Capability inventory: The AI agent can read/edit files and execute Bash commands.
- Sanitization: No sanitization or validation of the input code is described.- [EXTERNAL_DOWNLOADS]: The skill documentation references a repository on the author's official GitHub account (ruvnet) as a design reference.
Audit Metadata