nimble-web-search

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs real-time searches of public web and social sources (SKILL.md Core Capabilities / Focus Modes and examples like examples/basic-search.md) and instructs the agent to synthesize LLM answers and optionally extract full page content (include_answer=true, deep_search=true with the API response's "content" field), meaning untrusted, user-generated third-party content can be read and directly influence agent decisions and actions.