NYC

scientific-slides

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: 0.80). This skill explicitly ingests untrusted third‑party content — it instructs the agent to attach and incorporate user-provided or working-directory images/files via the --attach option and to use the research-lookup workflow to fetch public papers/citations (external web content) which the AI is expected to read and incorporate into slide generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:44 AM