ClawHub
Back to skill

Security audit

Gc Log Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused GC log analysis/reporting helper with no hidden execution, networking, persistence, or credential behavior found.

Install this if you want a Chinese-oriented GC log reporting workflow. Be aware it may activate for broad GC/JVM tuning or reporting prompts, and ask explicitly for a different language or narrower scope 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
93% confidence
Finding

The skill advertises very broad trigger phrases such as general GC troubleshooting, reporting, tuning advice, and leadership-summary requests, and says it should be used preferentially even when the user does not explicitly ask for the skill. That can cause over-invocation on common performance-analysis requests, leading the agent to bypass more appropriate tools or user intent boundaries and increasing the chance of unintended file access or unnecessary processing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill mandates a fixed Chinese-language output style by default rather than adapting to the user's language preference. While not directly enabling code execution or data exfiltration, this can override user intent, degrade usability, and cause the agent to produce outputs unsuitable for the requester or downstream recipients.

Content

No source excerpt is available for this finding.