web-article-translator
Warn
Audited by Snyk on Feb 15, 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 explicitly fetches arbitrary web pages via the mcp__web_reader__webReader tool (user-provided URLs) and ingests their public, untrusted article content into the translation workflow, exposing the agent to potential indirect prompt injection.
Audit Metadata