neuropixels-analysis

Warn

Audited by Snyk on Apr 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). The skill explicitly sends generated unit-visualization images to third-party LLM/vision APIs (e.g., Anthropic/OpenAI and Claude Code) as shown in SKILL.md and references/AI_CURATION.md via npa.analyze_unit_visually / batch_visual_curation, and it uses those untrusted model responses to classify/curate units which directly influence downstream curation and export decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 10:49 PM
Issues
1