ClawHub
Back to skill

Security audit

Power Automate Governance

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malware, but it can guide an agent to stop or migrate Power Automate flows during broad governance workflows, so it needs review before use.

Install only if you want the agent to help administer Power Automate governance, not just report on it. Before use, require the agent to list the exact tenant, environment, flows, and intended changes, and require explicit approval before stopping any flow, changing notification/monitoring fields, or migrating a flow into a solution.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The skill is presented as cache-based governance metadata management, but it also instructs the agent to invoke live operational tools such as stopping flows. That scope expansion is dangerous because a user expecting read/write governance tagging could unintentionally cause production automation outages through this skill.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The archive workflow defines 'archive' by stopping live flows, and the offboarding workflow similarly performs shutdown actions. In a governance skill, that creates a mismatch between user intent and real effect, increasing the risk of accidental denial of service against legitimate business processes.

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The maker offboarding workflow includes solution migration (`add_live_flow_to_solution`), which exceeds governance metadata maintenance and performs substantive changes to live platform configuration. That can alter deployment/ALM state unexpectedly and may have downstream operational or compliance consequences if invoked under a broad governance request.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger text contains a broad catch-all such as 'any task that involves writing governance metadata to flows,' which can cause the skill to activate for loosely related requests. Because the skill contains live modification capabilities, overly broad activation increases the chance that high-impact tools are loaded and suggested in contexts where the user did not intend administrative changes.

Static analysis

No suspicious patterns detected.