v0-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: 0.80). This skill queries an external Rube MCP server (e.g., RUBE_SEARCH_TOOLS against https://rube.app/mcp / Composio endpoints) to fetch tool schemas, recommended execution plans, and related data the agent is expected to read and act on, which is untrusted third-party content that could carry indirect prompt-injection payloads.
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 MCP server at https://rube.app/mcp at runtime (used by RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, and RUBE_MULTI_EXECUTE_TOOL) which returns tool schemas and can execute remote tools, so external content from that URL can directly control agent instructions or execute code.
Audit Metadata