CORE
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). This skill explicitly routes to web scraping and browsing of open/public sites (including Bright Data / Apify via the MCP skill and the Browser skill) so the agent will fetch and ingest untrusted third‑party content as part of its workflows (see SYSTEM/SCRAPINGREFERENCE.md and the SCRAPING / BROWSER entries in SKILL.md).
Audit Metadata