webmcp-security

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: 1.00). The skill's "Fetch live docs" instructions explicitly require fetching and web-searching public sites (e.g., https://webmachinelearning.github.io/webmcp/ and various web/GitHub searches), meaning the agent will read and act on untrusted third-party web content as part of its auditing workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 31, 2026, 06:10 AM
Issues
1