exa-get-contents
Warn
Audited by Snyk on Feb 16, 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 explicitly fetches and scrapes arbitrary public URLs (e.g., exa-ai get-contents examples like "https://techcrunch.com" and instructions to "crawl websites with subpages" using --livecrawl), causing the agent to read and summarize untrusted third‑party web content that could contain injected instructions.
Audit Metadata