researchers-verifier
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process data from external research files (e.g., RESEARCH.md, SOURCES.md) and web sources via the WebFetch tool. This creates a standard surface where malicious instructions embedded in third-party content could attempt to influence the agent's behavior.
- Ingestion points: Local research documents and external URLs retrieved via WebFetch.
- Boundary markers: No explicit delimiters or boundary warnings are implemented in the instructions.
- Capability inventory: Tools include Read, Edit, Write, Grep, Glob, WebFetch, and WebSearch.
- Sanitization: No specific content filtering or validation logic is applied to the retrieved external data.
Audit Metadata