ClawHub
Back to skill

Security audit

Xue Feng Skill Publish

Security checks for vulnerabilities and agentic risk

Overview

This skill is a career and gaokao-planning advisor, but it requires sensitive personal details and uses them in recommendations without clear user consent or opt-out guidance.

Review before installing if you are uncomfortable with a skill asking for or using gender, family background, family resources, location preference, or political-review/criminal-record-related circumstances in education and career advice. It does not appear to install code or persist data, but users should be told they can skip sensitive questions and should avoid sharing details not necessary for the recommendation.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation conditions are very broad and can trigger on routine education or career conversations without clear boundaries, causing the skill to collect and act on sensitive user data in contexts where specialized handling may not be expected. In this skill, that risk is amplified because later sections instruct gathering personal attributes such as gender, family background, location, and even criminal-record-related information, increasing the chance of unnecessary profiling or inappropriate advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs the system to use sensitive traits—including gender, family socioeconomic background, geographic preference, and criminal-record-related information—without an upfront warning, consent cue, or limitation statement. This is dangerous because users may disclose highly sensitive data without understanding it will shape recommendations, leading to privacy harm, discriminatory profiling, and potentially unlawful or unfair decision support.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is written entirely in Chinese and presents the skill as based on Chinese-language source material, but it does not indicate that the skill is region-specific or that users may choose another language. Under the policy, a language or locale constraint should be optional or clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.