ClawHub
Back to skill

Security audit

Skill Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese-language checklist for reviewing OpenClaw skill quality and does not install code, persist changes, or perform hidden actions.

Install only if you are comfortable with a Chinese-language reviewer that may read a target Skill's SKILL.md when you ask it to assess that skill. It should not need write access, credentials, network access, or automatic changes to other skills.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents the skill’s description, usage conditions, checklist, and output format exclusively in Chinese. Under the policy rule for natural-language violations, forcing a single language without user opt-in or justification is a language/locale policy issue.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

  1. 读取目标 Skill 的 SKILL.md
    bash
    # 假设要审查 weather skill
cat ~/.openclaw/skills/weather/SKILL.md
# 或
cat /opt/homebrew/lib/node_modules/openclaw/skills/weather/SKILL.md

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

  1. 读取目标 Skill 的 SKILL.md
    bash
    # 假设要审查 weather skill
cat ~/.openclaw/skills/weather/SKILL.md
# 或
cat /opt/homebrew/lib/node_modules/openclaw/skills/weather/SKILL.md

Static analysis

No suspicious patterns detected.