Security audit

Create-Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language guide for creating minimal OpenClaw skill files, with no bundled code, credential handling, persistence, or hidden execution behavior.

Before installing, note that this skill may guide the agent to create or modify files under a workspace skills directory. Review generated scripts if you choose to add them, but the published artifact itself is only a Markdown guide and appears low risk.

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 (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.
md
- 需要最小可用产物（默认仅 `SKILL.md`，必要时再加脚本）

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.
md
- 需要最小可用产物（默认仅 `SKILL.md`，必要时再加脚本）

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.
md
- 需要最小可用产物（默认仅 `SKILL.md`，必要时再加脚本）

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.
md
- 需要最小可用产物（默认仅 `SKILL.md`，必要时再加脚本）

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill defines very broad trigger phrases such as creating, rewriting, or optimizing skills without meaningful exclusion criteria, which can cause it to activate for many common requests. Over-broad activation can divert the agent into this skill unexpectedly, leading to inappropriate file generation or modification in contexts where a narrower or existing skill should have been used.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.