kaleido-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 instructs the agent to call RUBE_SEARCH_TOOLS on an external MCP (https://rube.app/mcp) and consume returned tool schemas, execution plans, and connection responses—external, potentially untrusted third-party content that the agent must read and act on.
Audit Metadata