webmcp-declarative-forms

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Before writing code" steps explicitly instruct fetching the public page https://webmachinelearning.github.io/webmcp/ and performing web searches for WebMCP/Chrome docs, meaning the agent is expected to read and act on open/public web content (web pages/search results) that could influence tool behavior.