web-article-translator
Warn
Audited by Snyk on Feb 16, 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 uses a webReader tool to fetch and ingest content from arbitrary public URLs (e.g., user-provided web pages/articles) and then reads/translates that untrusted third-party content as part of its workflow, exposing the agent to potential indirect prompt injection.
Audit Metadata