web-search

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

• Third-party content exposure detected (high risk: 0.90). Yes — SKILL.md explicitly shows apps that fetch and extract content from arbitrary public URLs (e.g., tavily/extract and exa/extract examples and the "Extract + Summarize" workflow) and then instructs agents/LLMs to read and summarize that extracted web content, exposing the agent to untrusted third-party pages that could carry indirect prompt-injection.