researching-markets
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather data from external websites using tools like
WebSearchandWebFetch. This creates a potential surface for indirect prompt injection if external websites contain malicious instructions. - Ingestion points: External data enters the agent context via
WebSearchandWebFetchas outlined in the 'Research Methods' section ofSKILL.md. - Boundary markers: The instructions do not define specific boundary markers or 'ignore' instructions for the data retrieved from external sources.
- Capability inventory: The skill is designed for research and report generation. It does not contain capabilities for file system modification, arbitrary command execution, or unauthorized network operations.
- Sanitization: The skill does not implement explicit sanitization or filtering logic for the content it retrieves.
- [SAFE]: No signs of direct prompt injection, obfuscation, credential theft, or malicious persistence mechanisms were found. The skill consists entirely of standard research guidelines and report templates.
Audit Metadata