convolo-ai-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill requires the configuration of a remote MCP server endpoint at https://rube.app/mcp. While this is an unverifiable third-party dependency, its use is downgraded to LOW as it is the primary intended purpose of the skill.
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill fetches tool schemas and execution plans at runtime. 1. Ingestion points: Tool definitions fetched via RUBE_SEARCH_TOOLS from rube.app. 2. Boundary markers: None provided to separate fetched metadata from system instructions. 3. Capability inventory: RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH. 4. Sanitization: Not specified; instructions prioritize exact adherence to fetched schemas.
- [NO_CODE] (SAFE): The skill consists entirely of markdown documentation and YAML configuration without any bundled executable scripts or binaries.
Audit Metadata