NYC

fda-database

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: 0.70). This skill directly queries public openFDA endpoints (see scripts/fda_query.py and scripts/fda_examples.py calling https://api.fda.gov/* such as drug/event.json, food/event.json, animalandveterinary/event.json, etc.) and ingests/display user-submitted/untrusted adverse-event and free-text reports as part of its workflows, so it clearly consumes untrusted third-party content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:04 PM