exa-search
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The provided skill file contains only metadata, installation instructions, and documentation. It does not contain any executable scripts, shell commands, or logical implementations within the provided markdown.
- [EXTERNAL_DOWNLOADS]: The installation guide directs the agent to fetch the skill from an external repository located at
BenedictKing/exa-searchvia thenpx skills addcommand. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to perform semantic searches and ingest content from the Exa API into the agent's context. This creates a surface for potential indirect prompt injection from the retrieved web content.
- Ingestion points: External data retrieved from the Exa API search results.
- Boundary markers: None defined in the skill documentation.
- Capability inventory: No file system, subprocess, or internal network capabilities are defined in the provided markdown file.
- Sanitization: None defined in the skill documentation.
Audit Metadata