slack-automation
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill reads and acts on user-generated Slack content (e.g., via SLACK_SEARCH_MESSAGES, SLACK_FETCH_MESSAGE_THREAD_FROM_A_CONVERSATION, and SLACK_FETCH_CONVERSATION_HISTORY as required in the Search and React workflows), so untrusted third-party messages could influence tool decisions and enable indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires connecting to and calling the MCP endpoint https://rube.app/mcp at runtime (e.g., "Always call RUBE_SEARCH_TOOLS first") to fetch tool schemas that directly determine agent instructions and available actions, making it a required external dependency that can control the agent.
Audit Metadata