tdd-london-chicago
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its data processing workflows.
- Ingestion points: The skill instructions in SKILL.md involve reading and processing external source code files (e.g.,
src/domain/Order.ts) and test requirements provided by the user. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the source code or metadata being processed.
- Capability inventory: The skill has coordination capabilities via the
TaskandFleetManagerAPIs to generate and modify implementation code and tests. - Sanitization: No sanitization or validation of the input source code is present, allowing instructions embedded in code comments or strings to potentially influence agent behavior during the Red-Green-Refactor cycle.
Audit Metadata