segmetrics-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill instructs the user to add an external MCP server endpoint (https://rube.app/mcp). While this is the primary purpose of the skill, the domain is not part of the predefined trusted source list.
  • REMOTE_CODE_EXECUTION (LOW): The skill utilizes tools like RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH which execute operations on a remote environment. This is the intended behavior for interacting with the Composio/Segmetrics ecosystem.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill possesses an attack surface where instructions could be embedded in the data retrieved from the remote server.
  • Ingestion points: Tool schemas and use-case search results returned by RUBE_SEARCH_TOOLS.
  • Boundary markers: Absent; the skill does not define specific delimiters to separate tool-provided data from system instructions.
  • Capability inventory: The skill uses RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH which can perform various automated actions based on input from the search results.
  • Sanitization: No sanitization or validation of the remote data is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM