researching-on-the-internet

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to perform WebSearch/WebFetch and to consult public community sources (e.g., Stack Overflow, forums, public documentation and links) to gather and interpret internet content, which are untrusted third-party sources that could carry indirect prompt injections.