NYC

expo

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: 0.70). The skill explicitly advises consuming external public APIs (notably "External APIs (like Open Food Facts)" and localized endpoints such as "us.openfoodfacts.org") and instructs the agent/developer to read and filter those responses, which are public/user-contributed and thus untrusted third-party content the agent would interpret at runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:33 AM