Writing Papers
Warn
Audited by Snyk on Mar 6, 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). The SKILL.md "Sources" section explicitly directs subagents to fetch content from public third‑party sources (ArXiv, Anna's Archive, Exa Search, and general web search), and the Subagent Processing and Citation Verification steps require the agent to read and act on that untrusted web content to verify quotes/claims and drive review decisions.
Audit Metadata