NYC

selection-randomizer

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: 1.00). The skill explicitly ingests and reads arbitrary Google Sheets, CSV/Excel files and plain lists (e.g., "Pick a random row from this Google Sheet" with a Sheet URL), which are untrusted, user-generated third‑party sources that the agent must parse as part of its workflow, allowing potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:16 PM