seat-geek-automation
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). This skill connects to the external SeatGeek toolkit via RUBE_MANAGE_CONNECTIONS and invokes tools (e.g., RUBE_MULTI_EXECUTE_TOOL) to fetch and interpret live SeatGeek data from a public third-party service, exposing the agent to untrusted third-party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill requires a runtime connection to the MCP server at https://rube.app/mcp and uses RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL to fetch tool schemas and have the remote MCP execute tools (i.e., the external server can directly control agent behavior and run remote code), so this URL is a required runtime dependency that controls prompts/execution.
Audit Metadata