tdd-workflows-tdd-red
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable to ingest user input and interpolates it into a prompt template for a test-automation sub-agent. This design creates an indirect prompt injection surface because it lacks boundary markers or instructions to isolate the user's input from the agent's instructions. Ingestion points:$ARGUMENTSvariable in the prompt template. Boundary markers: None provided. Capability inventory: The skill utilizes thetest-automatorsub-agent via the Task tool to generate executable code. Sanitization: No sanitization or validation of the input is performed before interpolation.
Audit Metadata