exa

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly uses Exa's neural web search and "Get Content" scripts to fetch and extract full text from arbitrary public URLs and sources (categories include tweets, personal-site, news, GitHub, PDFs), so the agent will ingest untrusted third‑party content that could contain instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:15 AM