ClawHub
Back to skill

Security audit

Copilot Studio Agent Creator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for creating Microsoft Copilot Studio agents, with disclosed but important cautions around autonomous triggers and maker credentials.

Before following the trigger and Power Automate sections, confirm which account's credentials will run each action, prefer user-scoped permissions where available, limit trigger scope, and review data exposure and billing before publishing.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly instructs users to configure autonomous event triggers that execute using the agent maker's credentials, which can cause the published agent to access or act on data beyond an end user's own permissions. Although the document later mentions this risk, the warning is not prominent or upfront at the point where triggers are introduced and configured, increasing the chance of accidental privilege misuse or data exposure.

Static analysis

No suspicious patterns detected.