exa-research

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a standard workflow for web research and discovery using Exa tools. It contains no executable code, shell commands, or obfuscated content.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from external websites.
  • Ingestion points: Content retrieved from the web via web_search_exa and web_fetch_exa tools.
  • Boundary markers: The instructions do not explicitly require the use of delimiters or instructions to ignore embedded commands in fetched content.
  • Capability inventory: The skill uses search and retrieval tools; no high-risk capabilities such as file system writes or subprocess execution are defined.
  • Sanitization: No content sanitization or validation steps are specified for the retrieved web data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 06:38 AM
Security Audit — agent-trust-hub — exa-research