flowstudio-power-automate-governance

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and registration pages on the official FlowStudio domain (mcp.flowstudio.app). These are informative links related to the skill's primary purpose and do not involve remote code execution.
  • [DATA_EXPOSURE]: The skill correctly instructs the user to store the required FLOWSTUDIO_MCP_TOKEN in an environment variable rather than hardcoding it. Access to flow metadata (owners, connections, security configurations) is restricted to the intended FlowStudio tools for audit purposes.
  • [COMMAND_EXECUTION]: The skill uses specialized store_* tools to perform operations. It does not invoke arbitrary shell commands or system-level processes.
  • [PROMPT_INJECTION]: The skill processes external data such as flow descriptions, display names, and hashtags which are authored by users in Power Automate. While this presents an indirect prompt injection surface where a malicious user could embed instructions in a flow description, the skill is limited to governance metadata writes and does not have the capability to execute instructions found within that data. Severity is assessed as LOW.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:49 AM