idea-evaluator
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect injection as it processes untrusted user input (the 'idea') during the debate workflow.
- Ingestion points: Untrusted user input enters the agent context via the idea description in
SKILL.md. - Boundary markers: The skill does not utilize explicit delimiters or 'ignore' instructions to isolate user input.
- Capability inventory: The skill uses only native LLM text generation and does not have access to any external tools, file system, or network resources.
- Sanitization: No sanitization or escaping of the user-provided idea is performed.
Audit Metadata