tdd
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for auditing and executing existing test suites and production code. Because these files are provided by the user or reside in the local environment, they represent untrusted data that could contain malicious instructions designed to influence the agent's behavior during the audit process.
- Ingestion points: Test files, production source code, and auxiliary documentation like
AGENTS.mdare read during the 'Audit workflow' described intest-audit.md. - Boundary markers: The instructions do not specify any delimiters or safety prompts to ensure the agent ignores embedded instructions within the code or comments it processes.
- Capability inventory: The skill requires the agent to have file system access for reading and writing (
Edit one coherent batch) and terminal access for running code (Run the smallest affected test files). - Sanitization: No sanitization or filtering of the ingested content is recommended before the agent processes it.
Audit Metadata