endorsal-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [Unverifiable Dependencies] (LOW): The skill requires connecting to an external MCP server at 'https://rube.app/mcp'. This domain is not included in the trusted source list for GitHub organizations or repositories.
- [Indirect Prompt Injection] (LOW): The skill instructions direct the agent to fetch tool schemas and execution plans at runtime from the remote server, which could be used to influence agent behavior.
- Ingestion points: Data returned from 'RUBE_SEARCH_TOOLS' (SKILL.md).
- Boundary markers: Absent; the instructions tell the agent to follow returned execution plans and use exact field names.
- Capability inventory: 'RUBE_MULTI_EXECUTE_TOOL' and 'RUBE_REMOTE_WORKBENCH' (SKILL.md).
- Sanitization: Absent; no validation steps are defined for the dynamic schemas before execution.
Audit Metadata