gamma-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 instructs the agent to call RUBE_SEARCH_TOOLS against an external MCP server (e.g., https://rube.app/mcp) to fetch tool slugs, input schemas, and execution plans—dynamic third‑party content the agent must read and interpret, which could contain untrusted/user-provided data.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill requires a runtime connection to the external MCP server https://rube.app/mcp which provides tool schemas via RUBE_SEARCH_TOOLS and executes tools via RUBE_MULTI_EXECUTE_TOOL, so fetched remote content directly controls agent prompts/behavior and executes code.
Audit Metadata