anysearch-mcp-server

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly performs general web searches and URL content extraction (see "General Web Search" and the "extract
• URL Content Extraction" section in SKILL.md) and even lists an "ugc" domain, so it ingests untrusted public web/user-generated content that the agent is expected to read and that can influence subsequent actions.