exa-similar-finder
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to discover and process external web content, which presents a surface for potential indirect prompt injection vulnerabilities. \n
- Ingestion points: External content and web metadata retrieved through the 'exa_find_similar' tool as described in SKILL.md. \n
- Boundary markers: There are no explicit instructions for using delimiters or boundary markers to isolate retrieved content from the agent's internal instructions. \n
- Capability inventory: The skill utilizes the 'sandbase_call_tool' gateway for searching; no destructive actions, file system writes, or unauthorized network operations are present. \n
- Sanitization: The instructions prioritize attribution and evidence-based synthesis but do not detail specific sanitization or filtering steps for content obtained from external URLs.
Audit Metadata