gpt-trainer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly lists a "Create URL Data Source" action ("Create a URL data source for a chatbot to train from web content") indicating it ingests arbitrary public web pages (untrusted third‑party content) as part of its workflow, which the agent would read and could influence subsequent behavior.