Back to skill

Security audit

Power Automate Governance

Security checks for vulnerabilities and agentic risk

Overview

This governance skill is coherent and disclosed, but users should be careful because some workflows can stop live Power Automate flows.

Install this only for users who intentionally manage Power Automate governance with FlowStudio MCP. Before allowing the agent to stop flows, migrate flows into solutions, or bulk-update governance metadata, confirm the target flows, business owners, rollback plan, and notification recipients.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises activation for broad phrases like 'assign ownership', 'generate a compliance report', or 'any task that involves writing governance metadata to flows,' which can cause the agent to load a write-capable governance skill for loosely related requests. In context, this increases the chance of inappropriate tool selection and unintended metadata changes to production governance records, especially because the skill also includes operational actions such as updating records and stopping flows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This workflow recommends set_live_flow_state(..., state="Stopped") as a response to orphaned flows without an explicit warning that stopping a live flow can interrupt business processes, integrations, or compliance operations. In this skill's context, the action affects real Power Automate runtime state, so an agent following the playbook could cause immediate production impact from cached-store governance analysis.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The archive workflow defines 'archive' as stopping the live flow and tagging it, but the action step does not clearly warn that this disables automation and may break active business processes. Because the surrounding text frames this as cleanup guidance, an agent may treat it as low-risk housekeeping even though it performs a real service-disrupting action.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

In the offboarding workflow, the skill instructs the agent to stop flows when decommissioning, but it does not require an explicit warning that this can halt still-needed automations during personnel transitions. Offboarding is a high-risk context because ownership changes are time-sensitive and easy to misclassify, making accidental shutdown of important flows more likely.

Content

No source excerpt is available for this finding.