ClawHub
Back to skill

Security audit

Meta Cognition Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a mostly documented manual interface for a metacognition knowledge workflow, with no implemented hidden execution, persistence, or data access behavior found.

Before installing, confirm you are comfortable with a Chinese-language skill intended to front a broader metacognition/Cron workflow. If future versions implement the advertised collection and integration actions, they should clearly disclose contacted sources, local output paths, and whether any skill or memory updates require confirmation.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly advertises manual triggering of collection, analysis, and integration workflows, and later points users to local execution logs, but it does not disclose that these actions may access external resources or write artifacts to local storage. This creates a transparency and consent problem: users may invoke actions that cause network activity or persistent data creation without realizing the side effects, which can expose sensitive context, consume resources, or create audit/privacy issues.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. The entire skill interface, examples, and instructions are presented only in Chinese, with no indication that users may choose another language or that the locale restriction is intentional and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents the skill description entirely in Chinese, including headings and operational purpose, without offering any language choice or noting that the skill is intended only for Chinese-speaking users. That can violate a language/locale policy when users are not given an explicit opt-in or justification for the locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.