ClawHub
Back to skill

Security audit

臭肺·吐纳魄

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only research helper skill with no executable code, hidden install behavior, credential use, or destructive instructions.

Install this if you want a Chinese-oriented research and learning workflow. Review its broad activation wording if you only want explicit web-research requests to trigger it, and avoid using it for sensitive topics unless you are comfortable with external source lookup.

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

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation examples use broad natural-language triggers like asking to 'look up the latest AI technology' or 'learn quantum computing,' which can cause the skill to activate in many ordinary contexts without clear user intent boundaries. In a skill that performs information retrieval and knowledge ingestion, overly broad activation increases the chance of unintended tool use, unnecessary data fetching, or routing sensitive prompts into external search/research flows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language content of the skill is effectively Chinese-only, including description, usage instructions, and output guidance. This imposes a specific language/locale without any stated user opt-in or alternative, which can violate language-choice policies for general-purpose skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.