grey-haven-tool-design

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 references and designs for MCP tools that perform web scraping and browser automation—e.g., the "firecrawl" MCP (listed as "Web scraping, search") and example tools like browser_navigate(url...) and browser_extract(selector, format)—which would allow the agent to fetch and interpret arbitrary public web content (untrusted third-party input).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 11:14 PM