searching-web
Warn
Audited by Snyk on Mar 29, 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). This skill explicitly performs live web searches and URL crawling of open/public sources (INSTRUCTIONS.md shows web_search_advanced_exa with categories including "tweet"/"personal site" and the crawling_exa({url: ...}) example) and the fallback scripts/web-search.sh runs a gemini CLI search that fetches and summarizes external webpages, so the agent ingests untrusted third‑party content that can influence its subsequent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata