slack

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the required workflow uses ClawLink to fetch Slack content (e.g., slack_fetch_conversation_history, slack_fetch_message_thread_from_a_conversation, slack_search_messages) and injects that message text—authored by other Slack users—into the agent’s LLM context, creating an outsider free-text prompt-injection surface.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running remote code via npx (npx @useclawlink/cli ...) which fetches and executes the @useclawlink/cli package from the npm registry (see https://www.npmjs.com/package/@useclawlink/cli and https://claw-link.dev), so external code is executed at runtime and is a required dependency.