cometchat-react-nextjs

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires querying the external CometChat docs MCP (https://www.cometchat.com/docs/mcp) and fetching code/CSS from the public GitHub raw URL (raw.githubusercontent.com/cometchat/cometchat-uikit-react/v6/sample-app/...) and instructs the agent to read and act on that content as authoritative when generating code, so untrusted third‑party content can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs runtime fetching of authoritative sample app code from raw.githubusercontent.com/cometchat/cometchat-uikit-react/... and installation/usage of the CometChat docs MCP at https://www.cometchat.com/docs/mcp (and relies on running npx @cometchat/skills-cli which downloads and executes remote npm code), so external content fetched at runtime can directly control the agent's instructions/code.