safe-web-research
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from web search results and links, creating a potential surface for indirect prompt injection.
- Ingestion points: Web search results and external links processed as part of the research workflow.
- Boundary markers: No specific delimiters or instructions to treat external data as untrusted are defined.
- Capability inventory: The skill uses search and summarization tools; no file system access or code execution capabilities were detected.
- Sanitization: No explicit content sanitization or validation is mentioned for retrieved data.
Audit Metadata