ClawHub
Back to skill

Security audit

PowerShell Reliable Execution

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local PowerShell reliability guide with clear privacy cautions and no bundled executable payload.

Reasonable to install if you want PowerShell reliability patterns. Treat the checkpoint snippets as templates only, keep checkpoint files limited to non-sensitive progress state, and review any generated PowerShell before running it.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly claims that sensitive data should be excluded from checkpoints and logs, but the checkpoint example serializes and writes the entire $state object to disk without any filtering or redaction. If callers place credentials, tokens, API keys, or other secrets into that state object during long-running or resumable workflows, the example encourages persisting them in plaintext in the working directory, creating a realistic secret leakage risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.