tdd
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection due to its requirement to process untrusted external inputs while maintaining significant capabilities.\n
- Ingestion points: In SKILL.md, the skill is instructed to process a 'Feature request, bug report, PRD, issue, or implementation plan,' all of which are common vectors for untrusted data.\n
- Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings to mitigate the risk of the agent following instructions hidden within these inputs.\n
- Capability inventory: The agent is granted the ability to create and modify both production and test files, as well as to execute shell commands to run tests (SKILL.md).\n
- Sanitization: The provided documentation and instructions do not specify any validation, sanitization, or filtering steps for external content before it is processed.
Audit Metadata