decide
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project files and external web research results which are interpolated into prompts for parallel sub-agents.
- Ingestion points: Local project files (e.g., git history, architecture documents) and results from external web research.
- Boundary markers: The templates in references/debate-prompts.md use section headers like CONTEXT: but do not include explicit instructions to ignore instructions found within the data.
- Capability inventory: The skill involves spawning parallel sub-agents, performing web research, and writing consensus documents to the local file system.
- Sanitization: No sanitization or filtering of external or file-based content is mentioned before processing.
Audit Metadata