Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md ### 2. 检查 / 创建 `SKILL.md`
Security audit
Skills Cli
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent command-line helper for managing ClawHub skills, with no hidden code or automatic execution, but users should review publish and sync commands before using them.
Install only if you want a Chinese-language ClawHub CLI workflow helper. Before using its publish or sync suggestions, review the target skill folders for private prompts, secrets, proprietary files, and confirm the exact path because those commands can send local skill contents to ClawHub.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Rogue AgentSelf-Modification, Session Persistence
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md ### 2. 检查 / 创建 `SKILL.md`
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md ### 2. 检查 / 创建 `SKILL.md`
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md ### 2. 检查 / 创建 `SKILL.md`
Self-Modification
High
- Category
- Rogue Agent
- Confidence
- 85% confidence
- Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
- Content
md 可根据需要添加： - `--tags latest` - `--changelog "Update skills"` - `--bump patch|minor|major` ## 验证与故障排查（Verification & Troubleshooting）
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The activation guidance is broad enough to match generic phrases about managing skills, which can cause this skill to trigger when a more specific or safer skill would be more appropriate. Over-broad routing increases the chance of unintended command suggestions and can steer users toward state-changing actions without sufficient context.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The publish and sync sections recommend remote-state-changing commands without clearly warning that local skill contents may be uploaded to ClawHub. Users may unintentionally expose private code, secrets, internal prompts, or proprietary files if they run these commands on a broad skills directory.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The document switches into Chinese for most operational guidance while the frontmatter description is in English, effectively imposing a language choice without opt-in. This can violate a language/locale policy when users are not given an explicit option to receive guidance in their preferred language.
- Content
Static analysis
No suspicious patterns detected.