search-specialist
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill describes processes for fetching and synthesizing content from the web, creating a surface for indirect prompt injection.
- Ingestion points: External data enters the context via search results and the WebFetch tool mentioned in the strategies section.
- Boundary markers: No specific delimiters or safety instructions are provided to separate untrusted web data from the agent's internal instructions.
- Capability inventory: The skill involves deep content extraction, data parsing, and synthesis from arbitrary online sources.
- Sanitization: The skill does not define methods for sanitizing or escaping the retrieved content before it is processed by the agent.
Audit Metadata