implement
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates code implementations and pytest tests based on external plans and research. This creates a surface where malicious instructions embedded in external content could influence the agent's behavior.
- Ingestion points: Instructions in SKILL.md direct the agent to 'follow the plan' and 'read research'.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the external data are present.
- Capability inventory: The skill is designed for code generation and the creation of unit tests.
- Sanitization: No methods for sanitizing or validating the plan or research content are defined.
Audit Metadata