research-survey

Warn

Audited by Snyk on Apr 14, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly requires ingesting and synthesizing papers collected by the paper-navigator (see "Dependency: paper-navigator" and Stage 2: "Generate a complete draft ... using the top-30 most relevant papers" and Stage 3: "Expand each ... using all collected papers"), which are open/public third‑party documents the agent must read and use to drive drafting and action, so untrusted third‑party content could materially influence behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 05:44 AM
Issues
1