exa-unified-research
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional documentation and does not include any executable scripts, binary files, or programming code.
- [NO_CODE]: No code files (.py, .js, .sh, etc.) are included in the skill package; it functions solely as a set of prompt instructions and configuration guidelines for existing search tools.
- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized data access patterns were detected. The skill's focus on structured search and distillation of web content is consistent with its stated purpose of unified research.
- [SAFE]: While the skill provides a framework for ingesting untrusted web data (a potential surface for indirect prompt injection), it includes defensive strategies such as token isolation, result distillation, and tool restrictions to mitigate context pollution.
Audit Metadata