ai-app

Warn

Audited by Snyk on Mar 31, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md Phase 1.2 and 1.5) explicitly instructs the agent to fetch public web pages such as https://modelcontextprotocol.io/sitemap.xml and "fetch specific pages" / "Use web search and WebFetch as needed", meaning the agent will ingest open, third-party web content which can materially influence tool design and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 31, 2026, 08:38 AM
Issues
1