research
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and merge user-provided field definition files (Step 3) into the research framework. This creates an attack surface where instructions embedded in external data could potentially influence subsequent agent actions during deep research.
- Ingestion points: User-supplied field definition files read and merged in Step 3.
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the user-provided files.
- Capability inventory: The skill maintains the ability to write YAML configuration files to the workspace and launch background web-search agents.
- Sanitization: No explicit sanitization or content validation for the user-provided data is documented in the workflow.
Audit Metadata