cometchat-react-reactjs

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly requires fetching and interpreting live third-party content (the CometChat docs MCP at https://www.cometchat.com/docs/mcp and sample app files via raw.githubusercontent.com) as part of its mandatory workflow, and those external files directly determine component wiring, props, and actions — creating a clear avenue for indirect prompt-injection from public web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly tells the agent at runtime to fetch and inject sample-app source via URLs such as https://raw.githubusercontent.com/cometchat/cometchat-uikit-react/v6/sample-app/src/components/... and to install the docs MCP from https://www.cometchat.com/docs/mcp — remote content that directly supplies code/instructions the skill requires to generate or adapt integration code.