supportivekoala-automation

Warn

Audited by Snyk on Feb 17, 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 requires calling RUBE_SEARCH_TOOLS against the Rube MCP server (https://rube.app/mcp) and ingesting the returned tool schemas/recommendations from Composio (e.g., composio.dev/toolkits/supportivekoala), so the agent will read and act on remote third-party content that could be untrusted.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 08:06 AM