discordbot-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [Unverifiable Dependencies & Remote Code Execution] (LOW): The skill requires connecting to an external MCP server (https://rube.app/mcp). While necessary for the primary function of the skill, this is a third-party dependency not found in the trusted sources list.
- [Indirect Prompt Injection] (LOW): The skill demonstrates a surface for indirect prompt injection by relying on external data to guide the agent's behavior.
- Ingestion points: Tool schemas and execution plans returned by the RUBE_SEARCH_TOOLS command.
- Boundary markers: Absent; the instructions tell the agent to follow the schemas and plans from search results directly.
- Capability inventory: Discord bot automation (messaging, management) and remote tool execution via RUBE_MULTI_EXECUTE_TOOL.
- Sanitization: Absent; the skill lacks validation or sanitization steps for the data returned from the external search service.
- [Dynamic Execution] (LOW): The core workflow involves discovering and executing tools dynamically at runtime via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH based on computed tool slugs.
Audit Metadata