tdd-workflows-tdd-green
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted test data.
- Ingestion points: The
$ARGUMENTSvariable insub-skills/implementation-playbook.mdaccepts external data representing failing tests. - Boundary markers: Absent. The untrusted data is interpolated directly into the prompt for the subagent without delimiters (like XML tags) or instructions to ignore embedded commands.
- Capability inventory: The skill utilizes a
test-automatorsubagent (identified insub-skills/implementation-playbook.md) which possesses the capability to generate and execute code and tests. - Sanitization: No validation or sanitization is performed on the test data before it is passed to the subagent.
Audit Metadata