ifood

Warn

Audited by Snyk on Apr 21, 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's SKILL.md instructs the agent to use the Membrane CLI to connect to iFood and run actions (e.g., "membrane action run ...") that fetch iFood Records and return an "output" field from the third-party iFood service, so the agent will read and act on untrusted third-party data from iFood.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 11:41 AM
Issues
1