webmcp-authentication
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: 0.90). Yes — the SKILL.md "Before writing code" section explicitly instructs fetching live docs from https://webmachinelearning.github.io/webmcp/ and performing web searches (e.g., "web-search
webmcp authentication session cookies browser agent"), so the agent is required to ingest open/public third‑party web content that could materially influence tool registration and runtime behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata