skills/ruvnet/ruflo/agent-workflow/Gen Agent Trust Hub

agent-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows standard procedures for defining an agentic workflow specialist. All identified tools (MCP) are namespaced under the 'flow-nexus' prefix, which is consistent with the vendor's provided context.
  • [COMMAND_EXECUTION]: The agent is equipped with tools to create and execute workflows (mcp__flow-nexus__workflow_create, mcp__flow-nexus__workflow_execute). While these perform actions, they are restricted to the intended environment of the workflow platform and do not involve arbitrary shell command execution.
  • [PROMPT_INJECTION]: No evidence of instructions designed to bypass safety filters, extract system prompts, or override core agent constraints was found.
  • [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or execute remote scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:32 PM