gpt-trainer
Warn
Audited by Snyk on Apr 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's documentation explicitly includes a "Create URL Data Source" action that creates a URL data source "for a chatbot to train from web content" and the Membrane action workflow (search/run actions and create actions) lets the agent ingest arbitrary public web pages, which could contain untrusted user-generated instructions that influence model behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata