Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 必须：`SKILL.md`（技能元数据文档）
Security audit
create skill
Security checks for vulnerabilities and agentic risk
Overview
This is a straightforward Chinese-language OpenClaw skill-creation guide with disclosed, purpose-aligned file and registry changes.
Install this only if you want a Chinese-language assistant that can help create or update OpenClaw skill files. Review proposed file and registry changes before approving them, especially because new skills can change future agent behavior.
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
- 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 (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger phrases are generic everyday terms like '创建技能' and '新建技能', which can accidentally match ordinary user conversation and invoke the skill without clear intent. In a skill that can generate files and update a registry, unintended activation creates a real integrity and safety risk even though it is not an exploit in the code-execution sense.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill describes generating files and updating the skill registry but does not prominently warn users up front that it performs workspace-modifying actions. This can mislead users into invoking a mutating skill without informed consent, increasing the chance of accidental file changes or unauthorized project state modifications.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The title, description, triggers, examples, and usage guidance are all written in Chinese, and the sample interaction assumes Chinese-language use. The file does not state that the skill is region-specific or offer an opt-in or alternative language, which can violate language/locale flexibility expectations.
- Content
Static analysis
No suspicious patterns detected.