MCP Development Skill

Warn

Audited by Snyk on Mar 10, 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.md explicitly defines readable Resources (e.g., the "Resources" section and resource template using "github://repo/{owner}/{repo}/..."), shows a "Read a resource" client integration example that reads GitHub content, and lists common servers including "github" and "puppeteer (Web scraping)", which together demonstrate the agent will ingest untrusted public/user-generated web content that can influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:56 AM