highergov-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). The skill explicitly instructs the agent to call RUBE_SEARCH_TOOLS and other Rube MCP endpoints (e.g., https://rube.app/mcp) and to read tool schemas and toolkit docs from Composio (composio.dev), which causes the agent to ingest external public tool/schema content that could contain untrusted or malicious instructions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires configuring and calling the MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL), which returns tool schemas and execution plans that directly control agent prompts and can trigger remote tool execution on that server.
Audit Metadata