Media

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The Essay workflow (Art/Workflows/Essay.md) mandates "deeply read the full blog post, essay, or input material" and explicitly requires running the CSE-24 step with "/cse [paste the content or URL]" — which instructs the agent to ingest arbitrary external URLs/content and use the extracted narrative to drive prompt construction and generation, exposing the agent to untrusted third‑party content that can influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 11:02 PM