exa-search

Warn

Audited by Snyk on Feb 15, 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 uses Exa methods like search_and_contents and get_contents (references/contents.md and sdk-patterns.md) to fetch full page text, highlights, and summaries from arbitrary public URLs and categories (including user-generated sources like "tweet", Medium, GitHub, dev.to), so the agent will read untrusted third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:15 PM