implement
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied specifications and tickets (mentioned in
SKILL.md), which acts as an ingestion point for potentially untrusted data. While this is the core functionality of the skill, the instructions do not specify boundary markers or sanitization logic to handle embedded instructions within these inputs.\n - Ingestion points: Project specifications and ticket descriptions provided by the user.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined in the instructions.\n
- Capability inventory: The skill is authorized to execute git commands, run test suites, perform typechecking, and call other development-focused tools (/tdd, /code-review).\n
- Sanitization: No automated or manual sanitization steps for the input data are mentioned.
Audit Metadata