WSL-PowerShell Controller

• Outcome: Review
• Latest audit: Sep 11, 2026 · 7:51 PM UTC
• Version: 1.0.1

Overview

This skill does what it claims, but it gives an agent broad Windows PowerShell control from WSL without enough scoping or confirmation safeguards.

Install only if you intentionally want an agent to run Windows PowerShell from WSL. Treat it as high-authority: require explicit approval for file writes, process killing, privilege elevation, script execution, and execution-policy bypass, and prefer a pinned, verified release rather than cloning the mutable main branch.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review

Findings (2)

T08 · Insecure Dependencies

Warning

• Location: README.md:26

Finding

Unverified Installation from Mutable Third-Party Sources

Content

View full analysis

Remediation

View remediation

T09 · Insecure Skill Coding Practices

Warning

• Location: psctl.sh:180

Finding

Implicit PowerShell Execution-Policy Bypass

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The README prominently demonstrates commands that copy files, create files, start processes, stop processes, and perform network operations, but the warnings are generic and appear later rather than directly attached to risky examples. In an agent skill context, such examples can normalize or encourage execution of host-impacting Windows commands from WSL, making accidental destructive actions more likely.

Content

No source excerpt is available for this finding.

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 171)May include surrounding context.

md

Issues and Pull Requests are welcome!

1. Fork the project
2. Create feature branch (`git checkout -b feature/AmazingFeature`)
3. Commit changes (`git commit -m 'Add some AmazingFeature'`)
4. Push to branch (`git push origin feature/AmazingFeature`)
5. Open Pull Request

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The README says the agent can 'automatically use this skill based on user requests' but does not define narrow triggers, approval requirements, or safe operation boundaries. Because this skill bridges WSL to Windows PowerShell, vague activation criteria can cause an agent to invoke powerful host-level commands in response to loosely related prompts, increasing the chance of unintended system changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

This skill explicitly enables execution of Windows PowerShell from WSL and includes examples for file copying, file creation, process termination, and privilege elevation. While the content appears instructional rather than overtly malicious, it meaningfully expands an agent's ability to modify the host system and could be abused to perform destructive or unauthorized actions if invoked without strong user consent and safety guardrails.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

This code runs a provided script file via PowerShell and also executes a user-supplied command string directly. Although help text documents usage, it does not warn that execution may run arbitrary code on the Windows host, potentially affecting files or system state, and there is no confirmation prompt before execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 87% confidence

Finding

The file presents its primary instructions and headings in Chinese, and there is no indication that language choice is optional or that the skill is intentionally limited to a Chinese-speaking context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The script's comments, help output, and operational messages are all presented only in Chinese. This imposes a specific language on users without offering a locale choice or documenting that the tool is intended for a Chinese-only environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.