sentry-automation
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to the external MCP endpoint https://rube.app/mcp and explicitly instructs calling RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas from that server, which can directly control the agent's prompts/actions.
Audit Metadata