llm-app-patterns

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 defines and uses a "search_web" tool in the Function Calling Pattern (and ReAct examples) that instructs the agent to fetch and consume web search results/observations as part of the agent loop, exposing it to untrusted public web content that can influence subsequent actions.