Back to skill

Security audit

PowerShell 安全调用

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners flagged advice to use a full-access context and could not fully inspect some content.

Review the full-access recommendation and consider whether you can use the skill without following it. Scanning was incomplete: only 1 of 3 components was fully inspected, and a static analysis step was degraded. The suspicious verdict indicates review is warranted; it does not establish malicious intent.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Mapped-drive troubleshooting is used to justify switching to a full-access execution context.

High
Category
Prompt Injection
Confidence
90% confidence
Finding

The skill recommends switching to a current-user/full-access execution mode when a mapped drive is unavailable in an automation or sandbox account. This conflates session-specific drive visibility with insufficient permissions and could lead an agent to weaken isolation unnecessarily, exposing additional files or credentials to subsequent operations. Although legitimate troubleshooting alternatives are provided and no escalation is executed directly, the recommendation lacks an explicit authorization requirement or least-privilege constraint.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

md
For uncommon cases and complete examples, read `reference.md`.