ClawHub
Back to skill

Security audit

Performance

Security checks for vulnerabilities and agentic risk

Overview

This is a short, disclosed performance-evaluation design guidance skill with no code, install behavior, credentials, network calls, or hidden authority.

Before installing, note that this skill may be invoked for a fairly broad range of performance-evaluation design tasks. Review its Chinese-language guidance for fit with your HR process and local compliance needs, especially around personal information minimization.

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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description says the skill should be invoked '在开展绩效考核设计相关工作时调用' ('invoke when carrying out performance evaluation design related work'), which is a broad condition rather than a specific trigger phrase or constrained context. It does not provide explicit examples, exclusions, or invocation boundaries, which could lead to unintended activation across a wide range of everyday HR or management discussions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.