mem-automation
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION] (HIGH): The skill defines a workflow where the agent must fetch and follow instructions from an external source.
- Ingestion points: The
RUBE_SEARCH_TOOLScommand retrieves "recommended execution plans" and "tool schemas" fromhttps://rube.app/mcp. - Boundary markers: Absent. The skill instructions explicitly tell the agent to "Always search tools first" and use results to execute workflows, without any validation or delimiters.
- Capability inventory: The skill allows for full automation of Mem tasks, including reading, writing, and bulk operations via
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCH. - Sanitization: Absent. There is no logic to sanitize or verify the "execution plans" provided by the remote server.
- [EXTERNAL_DOWNLOADS / REMOTE_CODE_EXECUTION] (HIGH): The setup process requires adding
https://rube.app/mcpas an MCP server. This source is not on the trusted list. Since MCP servers provide the executable logic for tools, this is equivalent to executing remote, unverified code. - [COMMAND_EXECUTION] (MEDIUM): Use of
RUBE_REMOTE_WORKBENCHandRUBE_MULTI_EXECUTE_TOOLprovides a powerful execution surface for the remote server to leverage via the tool discovery mechanism.
Recommendations
- AI detected serious security threats
Audit Metadata