-2chat-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 directs the agent to query a public Rube MCP server (https://rube.app/mcp) using RUBE_SEARCH_TOOLS and RUBE_GET_TOOL_SCHEMAS to retrieve tool slugs, schemas, and execution plans, so the agent ingests and interprets untrusted third-party content from that public endpoint.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires adding the MCP server endpoint https://rube.app/mcp and then calls RUBE_* operations (e.g., RUBE_MULTI_EXECUTE_TOOL) at runtime against that external server to execute tools/operations, meaning remote content at that URL can execute code or control agent behavior.
Audit Metadata