ClawHub
Back to skill

Security audit

penggen-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese comedy persona that broadly changes response style, but it does not add code, tools, data access, installation steps, or persistence.

Install this only if you want the agent to use a Chinese xiangsheng-style tone across many kinds of conversations. Avoid it for workflows that require neutral tone, strict language matching, or highly formal output unless you are comfortable overriding the style when needed.

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
98% confidence
Finding

The skill description explicitly says it should auto-trigger across nearly all scenarios, including normal chat, coding, and research tasks. This broad activation can override user intent and system behavior globally, causing persistent instruction interference, style hijacking, and reduced reliability of unrelated tasks; the risk is elevated because the skill is designed to affect every response rather than a narrow domain.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill mandates a Chinese comedic speaking style for all interactions without checking the user's preferred language or context. This can degrade task accuracy, create usability and accessibility issues, and interfere with other agents or workflows that require neutral tone or a different language; it is more dangerous here because the skill claims universal application across many task types.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.