slack-automation

Warn

Audited by Snyk on Feb 15, 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). The skill explicitly reads and searches Slack user-generated messages and threads (e.g., SLACK_SEARCH_MESSAGES, SLACK_FETCH_MESSAGE_THREAD_FROM_A_CONVERSATION, SLACK_FETCH_CONVERSATION_HISTORY), exposing the agent to untrusted third-party content from workspace users that could carry indirect prompt-injection.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill requires adding and using the MCP server at https://rube.app/mcp and instructs calling RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas from that endpoint, meaning remote content from that URL directly controls the agent's available tools/instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:22 PM