ClawHub
Back to skill

Security audit

AI Deep Learning Methodology

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language research workflow skill with no executable code, persistence, or hidden authority, though it may activate broadly for learning requests.

Install this if you want a structured research-study workflow. Before using it, decide whether you want the full deep-research process or just a quick answer, and avoid uploading private, copyrighted, or sensitive documents to third-party knowledge-base tools unless you are comfortable with that service's data handling.

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
  • 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

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match many normal research or learning requests, which can cause the skill to activate unexpectedly and steer conversations into its prescribed workflow. While this is not direct code execution, over-broad routing can override user intent, increase unnecessary tool use, and create opportunities for inappropriate data gathering or external lookups when a simpler response was desired.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill metadata and description prescribe Chinese-language behavior without indicating that this should depend on the user's language preference. This can degrade usability, mis-handle user intent, and in multilingual contexts may cause the agent to disclose or transform content in an unintended language, though the security impact is limited.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.