AGENT LAB: SKILLS

excalidraw-diagram-generator

Warn

Audited by Snyk on Feb 15, 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 instructs users to download and load public Excalidraw libraries from https://libraries.excalidraw.com (place .excalidrawlib files under skills/.../libraries/) and the provided scripts (e.g., split-excalidraw-library.py and add-icon-to-diagram.py) explicitly load and ingest those third-party icon JSON files, so the agent is expected to read/interpret untrusted, public content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:12 PM