new-learning

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

• Third-party content exposure detected (high risk: 0.80). The skill's Process step 3 ("Search for current resources") requires using web search to fetch up-to-date articles, tutorials, docs, and project ideas from the public web, which the agent will read and use to generate learning suggestions and backlog entries, exposing it to untrusted third-party content that could carry indirect prompt injection.