ClawHub
Back to skill

Security audit

Microsoft Learn

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps agents search Microsoft Learn documentation, with ordinary setup risk from an unpinned npm CLI but no evidence of hidden or malicious behavior.

Before installing, consider pinning @microsoft/learn-cli to a reviewed exact version and prefer a local project install or controlled environment over a global npm install. Expect the skill to make Microsoft documentation lookups for a broad range of Microsoft-related questions.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
skill.md:17
Finding

Unpinned npm Package Installation and Runtime Execution

Content
View full analysis
Remediation
View remediation

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger scope is extremely broad (any MS technology question), which can cause the skill to activate for loosely related prompts and unnecessarily route user queries into CLI-backed retrieval behavior. Overbroad activation increases attack surface, can lead to unintended external lookups, and may cause the agent to use this skill in contexts where a narrower or safer tool would be more appropriate.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

Using npx @microsoft/learn-cli without a pinned version allows retrieval and execution of whatever package version is current at invocation time. If the package is compromised, typo-resolved unexpectedly, or a breaking/malicious release is published, the agent could run untrusted code during setup or use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.