ClawHub
Back to skill

Security audit

Documentation

Security checks for vulnerabilities and agentic risk

Overview

This is a local documentation-assistance skill with limited read access and no evidence of payment, network, persistence, or destructive behavior.

Install this if you want a Chinese-language local documentation helper. Expect it to read relevant local project files when you ask it to use them, but the reviewed artifacts do not show network upload, payment handling, persistence, or credential use.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared purpose describes a documentation-assistance skill that should help with structuring or organizing technical documents. The supplied code does not implement any documentation-related processing, analysis, or generation. Instead, it only emits informational text about the skill being free and how to invoke a workflow, then exits. This is a materially different primary purpose from the declared description, so it should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction "请使用中文和用户交互" forces a specific language for all interactions. The policy allows locale constraints only when the skill offers opt-in choice or clearly documents a justified regional limitation, neither of which is present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.