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