exa-unified-research
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a collection of search guidelines and query templates designed to interface with Exa research tools. It does not contain executable code, scripts, or commands.- [SAFE]: No evidence of prompt injection, data exfiltration, or credential harvesting was found. The instructions focus on refining search parameters and handling search results efficiently.- [SAFE]: The skill uses a progressive disclosure model to limit context size by reading only relevant reference files based on user intent, which is a standard performance optimization.- [SAFE]: The mention of a 'browser fallback' for authenticated or JavaScript-heavy content refers to standard agent capabilities and does not introduce new security risks within the skill's instructions.
Audit Metadata