tdd-harness
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest arbitrary user requirements (ideas, features, bugfixes) and translate them into committed code, GitHub Action workflows, and pull requests. This represents a vulnerability surface where malicious instructions embedded in a user's feature request could potentially influence the agent to generate backdoored code or insecure CI configurations.
- Ingestion points: User-provided descriptions of features, products, or bugfixes (processed by the orchestrator and passed to the
tdd-planandred-green-refactorskills). - Boundary markers: No specific delimiters or boundary markers are defined in the instructions to isolate user input from the agent's internal logic.
- Capability inventory: The skill (via sub-skills) has the capability to write files (plans, implementation, tests), commit to Git, push to remote repositories, and create GitHub Actions CI workflows (
.github/workflows/). - Sanitization: There is no mention of sanitization or validation of the user's input before it is used to generate executable code or infrastructure configuration.
Audit Metadata