ClawHub
Back to skill

Security audit

对抗性审查

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only workflow guide for getting adversarial review on important decisions, with no hidden install behavior or destructive capability.

Install only if you are comfortable with a skill that may ask your agent to spawn scoped reviewer subagents for important decisions. If Chinese is not your preferred working language, consider translating or adding a language preference note before use.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill content is written entirely in Chinese and does not indicate that language should follow the user's preferences, which can cause the agent to respond in a forced locale without user opt-in. In an interactive security or engineering workflow, this can reduce user comprehension, hide important caveats, and increase the chance that a user approves risky actions they do not fully understand.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.