academic-research
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: 1.00). The skill explicitly performs "Web search for papers" and accepts arbitrary "paper URL" inputs, meaning it fetches and ingests public third-party content (papers/web pages) which the agent will read and interpret as part of its workflow, exposing it to indirect prompt injection.
Audit Metadata