T08 · Insecure Dependencies
Warning
- Location
SKILL.md:12- Finding
Unpinned Global npm Dependency Installation
- Content
View full analysis
- Remediation
View remediation
Security audit
OpenClaw 工作流快速入门指南
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent Chinese onboarding guide for OpenClaw workflows and ClawHub publishing, with expected but user-visible install, login, publish, and verification steps.
Before installing or following the guide, verify the `clawhub` npm package source and version, avoid running global npm installs with elevated privileges, review any skill or resource directory for secrets before `clawhub publish`, and use broad commands like `clawhub update --all` only when you intend to update all installed resources.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (1)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- 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 (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - [ ] `SKILL.md` 存在且格式正确
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The manifest description and document title present the skill as a Chinese-only guide, and the rest of the instructions are written exclusively in Chinese. For a general onboarding skill, this imposes a specific language/locale without any user opt-in or documented regional justification, which matches the language-policy violation criteria.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
The skill includes commands to publish content to a remote registry and to verify results via networked services, but it does not clearly warn that these steps transmit local data and metadata to external systems. In an agent or automation context, this can lead to unintentional disclosure of proprietary content, internal metadata, or other sensitive material if users follow the workflow without understanding the external data flow.
- Content
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
md ## 参考资源 - TaskFlow 官方文档: `skills/taskflow/SKILL.md` - TaskFlow 示例: `skills/taskflow/examples/inbox-triage.lobster` - ClawHub 注册表: https://clawhub.com - 数字资源管理指南: `skills/digital-resource-management-guide/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
md - TaskFlow 官方文档: `skills/taskflow/SKILL.md` - TaskFlow 示例: `skills/taskflow/examples/inbox-triage.lobster` - ClawHub 注册表: https://clawhub.com - 数字资源管理指南: `skills/digital-resource-management-guide/SKILL.md` ---
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The description is written entirely in Chinese, which can impose a language expectation on users without any opt-in or alternative locale indicated in the manifest. Under the policy, locale or language constraints should either offer user choice or be clearly justified as region-specific.
- Content