app-integrations

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses the ClawLink CLI to access third-party apps (e.g., via OAuth-connected Gmail/Notion/Slack/Shopify) and then reads their content through ClawLink, which can include outsider-authored free text that the agent ingests into its LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs running "npx @useclawlink/cli" (a runtime npx install/execute of remote package code) and lists the npm package URL https://www.npmjs.com/package/@useclawlink/cli, so it clearly fetches and executes external code at runtime as a required dependency.