ClawHub
Back to skill

Security audit

Diting Performance Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language performance-management advisory skill with disclosed analysis workflows and no hidden execution, persistence, credential access, or destructive behavior.

Install only if you want a Chinese-language performance-management advisor. Treat its PIP, performance rating, promotion, compensation-adjacent, and termination-adjacent advice as decision support that should be reviewed by qualified HR, legal, or leadership stakeholders before use in real employee decisions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
This markdown file contains user-facing instructional content exclusively in Chinese, and nowhere indicates that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The manifest description includes Chinese content and an English 'Use when ...' directive but does not state any language-selection behavior or user opt-in. Under the language/locale policy, forcing or implicitly assuming a language without choice can be a natural-language policy concern.

Context-Inappropriate Capability

Low
Confidence
77% confidence
Finding
The manifest frames this skill as a绩效管理 expert that analyzes and advises on performance-management topics, and the rest of the file is primarily procedural guidance and analytical frameworks. At L258, the document explicitly tells the skill to use `web_search-plus` to search industry reports, which introduces an external information-retrieval capability not otherwise declared as part of this skill's scope.

Static analysis

No suspicious patterns detected.