ClawHub
Back to skill

Security audit

Xue Feng Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent college-major advice guide, but it requires and uses gender to shape consequential education and career recommendations in a way users should review carefully.

Review this skill before installing if you do not want education or career advice shaped by gender. Its web searches for current admissions and employment data are expected, but the mandatory gender question and gender-based recommendations should be treated as a policy and fairness concern, not as hidden malware.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly instructs the agent to use the user's gender to produce different education and career recommendations, including stereotyped assumptions about work environment, physical demands, and suitability of professions. This is risky because it drives consequential advice using a sensitive personal attribute without necessity, user opt-in, or safeguards against discriminatory treatment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The workflow makes gender a mandatory input ('缺一不可') for every consultation, forcing collection of sensitive personal data even when it is not required to answer the user's question. Mandatory collection increases privacy risk and enables downstream discriminatory profiling because the skill's later logic uses gender to gate or shape recommendations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.