doc-tdd-autopilot
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted data from multiple sources including user prompts, component specifications (docs/06_SPEC/), and implementation plans (IPLAN). These inputs are used to generate TDD documents and update project indexes (docs/07_TDD/TDD-00_index.md). The instructions do not specify the use of boundary markers or delimiters to isolate untrusted input, nor is there explicit sanitization mentioned. While the skill's capabilities are limited to document generation and it does not perform network operations or arbitrary code execution, maliciously crafted input could potentially influence the generated documentation or the subsequent automated audit/fix cycle.
Audit Metadata