NYC

tandoor-recipes

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). The skill fetches and parses recipes, meal plans, and shopping-list data from a user-specified Tandoor instance (TANDOOR_URL), which can contain untrusted/user-generated content (recipes, steps, ingredients) that the agent reads and interprets.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:50 AM