modelry-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill requires the configuration of an external MCP server endpoint (
https://rube.app/mcp). This is a remote dependency that controls the toolset available to the agent. - PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) by instructing the agent to fetch and adhere to "execution plans" provided by a remote source.
- Ingestion points: Data returned from the
RUBE_SEARCH_TOOLScall, specifically tool schemas and execution plans. - Boundary markers: Absent. The instructions do not provide delimiters or warnings to ignore instructions within the tool search results.
- Capability inventory: The skill utilizes
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCHwhich allow for complex tool execution based on remote data. - Sanitization: Absent. The agent is explicitly told to follow the schemas and plans returned by the server without validation.
Audit Metadata