ClawHub
Back to skill

Security audit

考点分析专家

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Chinese-language study-outline analyzer with no code execution, persistence, credential use, or hidden data access.

Install only if you want syllabus and exam materials analyzed into a Chinese JSON study map. Review outputs for accuracy before relying on predicted exam weights or question types.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill content, examples, field names, and instructions are all fixed in Chinese, with no indication that users may choose another language or locale. This can violate language/locale policy when a skill imposes a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description includes not only specific phrases but also the broad condition of 'directly sending teaching-outline text.' This lacks boundaries or exclusion conditions, so ordinary document sharing could unintentionally invoke the skill.

Content

No source excerpt is available for this finding.