tdd-workflows-tdd-cycle
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-supplied data via the
$ARGUMENTSvariable directly into prompts for various subagents (e.g., architect-review, test-automator, code-reviewer) without using delimiters or sanitization. This allows potentially malicious input to influence the instructions given to these subagents. - Ingestion points: User input is captured via the
$ARGUMENTSvariable and used throughoutSKILL.mdin prompts for requirements analysis, test design, and implementation phases. - Boundary markers: The instructions do not use delimiters or explicit "ignore embedded instructions" warnings when interpolating the user input.
- Capability inventory: The subagents invoked by this skill have capabilities including writing production code, creating test suites, and performing architectural reviews.
- Sanitization: There is no evidence of validation, filtering, or escaping of the user-provided input before it is passed to the subagent tools.
Audit Metadata