tdd-workflows-tdd-green
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external test data to guide code generation, creating an attack surface for indirect prompt injection. * Ingestion points: Failing tests are passed through the $ARGUMENTS variable in resources/implementation-playbook.md. * Boundary markers: Absent. The instructions do not define clear boundaries or specify that the agent should ignore instructions found within test inputs. * Capability inventory: The skill writes code to the filesystem and is designed to trigger test runners. * Sanitization: No sanitization is applied to the input tests.
Audit Metadata