Back to skill

Security audit

Skill Creator Plus

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide for creating and reviewing OpenClaw skills, with no bundled executable code, credentials, persistence, or hidden data access.

Install only if you want Chinese-language guidance for creating OpenClaw skills. Before publishing any skill generated with it, review the generated SKILL.md and _meta.json yourself, especially any credential paths, API domains, background-process declarations, and publish commands.

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
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: skill-creator-plus
description: "创建、编辑、优化或审查 OpenClaw AgentSkills 技能。当创建新技能或修改现有技能时触发。提供完整的工作流程指引:技能结构设计、frontmatter 规范、_meta.json 格式、ClawHub scanner 规则、渐进式披露设计、validation checklist 及发布流程。输出:SKILL.md + _meta.json。"
metadata: {"openclaw":{"emoji":"🛠️","requires":{"anyBins":[]}}}}
---

# skill-creator-plus

创建符合 ClawHub 规范的 OpenClaw 技能。按以下规则执行,不要跳过章节,不要发明规范中未列出的约定。

未提供技能

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 269)May include surrounding context.

好的 description 示例:

text
"Facebook Page manager: post, schedule, reply & get insights. Requires: powershell/pwsh. Reads ~/.config/fb-page/credentials.json (FB_PAGE_TOKEN, FB_PAGE_ID). FB_APP_SECRET for one-time setup only — delete afterward. Long-lived token; rotate periodically and immediately if host is compromised. Grant minimal permissions only. No data forwarded to third parties; all calls go to graph.facebook.com only."

_meta.json

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 413)May include surrounding context.

好的 description 示例:

text
"Facebook Page manager: post, schedule, reply & get insights. Requires: powershell/pwsh. Reads ~/.config/fb-page/credentials.json (FB_PAGE_TOKEN, FB_PAGE_ID). FB_APP_SECRET for one-time setup only — delete afterward. Long-lived token; rotate periodically and immediately if host is compromised. Grant minimal permissions only. No data forwarded to third parties; all calls go to graph.facebook.com only."

_meta.json

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description is entirely in Chinese and describes when the skill should trigger and what it provides, but it does not indicate that language is selectable or that Chinese is required for a region-specific use case. This creates a natural-language locale constraint without user opt-in, which matches the policy-violation category for language or locale restrictions.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 175)May include surrounding context.

md
- 所有 credential 要求在 description 中命名(文件路径 + 字段名)
- 区分 required vs optional 字段
- 任何脚本中无 token 字面值——运行时从磁盘读取
- 所有运行时文件权限限制(icacls/chmod 600)
- 长期 token:包含 rotation 指引和入侵时立即 rotation 说明

### 5. Persistence & Privilege

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 355)May include surrounding context.

md
- 所有 credential 要求在 description 中命名(文件路径 + 字段名)
- 区分 required vs optional 字段
- 任何脚本中无 token 字面值——运行时从磁盘读取
- 所有运行时文件权限限制(icacls/chmod 600)
- 长期 token:包含 rotation 指引和入侵时立即 rotation 说明

### 5. Persistence & Privilege