exa-web-search-free

Warn

Audited by Snyk on Apr 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: 1.00). The SKILL.md and references/examples.md explicitly describe tools (web_search_exa, get_code_context_exa, company_research_exa, crawling_exa) that fetch and extract content from public sites (e.g., GitHub, StackOverflow, arbitrary URLs like "https://example.com/article" and "https://anthropic.com/...") and the agent is expected to read and act on those results as part of its workflow, exposing it to untrusted third‑party content that could contain instructions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 15, 2026, 12:15 AM
Issues
1