ClawHub
Back to skill

Security audit

Wsl Shell Reliability

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Windows shell-selection guide with disclosed, purpose-aligned behavior and no executable payload or persistence.

Install this only if you want Codex to apply Windows shell-selection guidance. Review any generated commands that delete files, alter services or registry settings, install packages, or cross between WSL and Windows paths before allowing execution.

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
  • 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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger 'Any terminal execution task on Windows' is extremely broad and overlaps with routine activity, making it unclear when this skill should activate versus when other terminal-related skills should apply. The section does not provide narrowing constraints or negative examples to bound invocation scope.

Missing User Warnings

Medium
Confidence
81% confidence
Finding
The markdown documents POSIX-heavy examples including 'rm -rf' and later provides a PowerShell translation to 'Remove-Item -Recurse -Force', both of which are destructive operations. The skill does not include a user-facing warning that these examples can irreversibly delete data or that confirmation may be appropriate before execution.

Static analysis

No suspicious patterns detected.