ClawHub
Back to skill

Security audit

Metacognition Checker

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only metacognition coaching skill with no code execution, external access, persistence, or sensitive data handling.

Before installing, note that the skill may answer using Chinese phrasing from its examples unless your agent keeps responses in your requested language. Otherwise it is a low-risk, text-only coaching skill.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown skill includes substantial Chinese-only instructions, examples, and output templates alongside English content, but it does not state that responses should follow the user's preferred language or that the skill is intended for a Chinese-speaking audience. That can effectively impose a language/locale on some users without opt-in, which matches the policy-violation criterion for language choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.