postgrid-verify-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE] (SAFE): No malicious patterns or hardcoded credentials were found in the skill documentation.
- [EXTERNAL_DOWNLOADS] (LOW): The skill requires connecting to an external MCP server (rube.app). Users must trust the provider as this is a third-party endpoint.
- [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface. Evidence: 1. Ingestion points: Tool schemas and execution plans are ingested from RUBE_SEARCH_TOOLS. 2. Boundary markers: None present. 3. Capability inventory: Includes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH which allow remote actions. 4. Sanitization: No sanitization of the discovered tool schemas is mentioned.
Audit Metadata