exa-best-practices
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on how to use tools (
web_search_exa,web_fetch_exa) that ingest content from external, untrusted web sources. This creates a surface for indirect prompt injection, where instructions hidden on external websites could potentially influence the agent's behavior. - Ingestion points: Web search results and fetched page content retrieved via Exa tools.
- Boundary markers: The instructions do not define explicit delimiters or boundary markers to isolate untrusted web content from the system instructions.
- Capability inventory: The skill utilizes tools for web searching and content retrieval.
- Sanitization: No specific content sanitization or filtering mechanisms are described in the instruction file.
Audit Metadata