tdd-workflow
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user requirements to guide code generation and execution.
- Ingestion points: The 'Step 1: Write User Journeys' phase where the agent processes external requirements (e.g., 'As a user, I want...').
- Boundary markers: The instructions do not define clear delimiters or warnings to ignore malicious instructions embedded within the user journeys or feature requirements.
- Capability inventory: The skill utilizes shell commands (
npm test,npm run test:coverage) and directs the agent to implement code and tests based on external input. This combination allows for potential exploitation if an attacker provides instructions disguised as requirements that lead to malicious code implementation or command execution. - Sanitization: The skill lacks logic for sanitizing, validating, or escaping user-provided input before it is interpolated into code templates or used to trigger test runs.
Audit Metadata