Back to skill

Security audit

电商视频生成 Ecommerce Video

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed wrapper around the dLazy ecommerce-video CLI and hosted service, with normal but real dependency, API-key, and file-upload considerations.

Before installing, review the linked dLazy CLI source or npm package, prefer npx or an isolated environment if you do not want a global CLI, avoid running npm as an administrator, and only attach product files you are comfortable uploading to dLazy. Treat the saved dLazy API key like a credential and rotate or revoke it from the dLazy dashboard if needed.

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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:5
Finding
Third-Party npm Package Is Downloaded and Executed Without Integrity Verification<![CDATA[ ## Vulnerability Details **File Location**: `SKILL.md:5, 58-65`; mirrored in `SKILL-cn.md:5, 58-65` **Vulnerability Type**: Unverified third-party dependency execution **Risk Level**: Medium ### Vulnerable Code ```yaml metadata: {"clawdbot":{"emoji":"🛒","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/cli@1.2.3","installAlternative":"npx @dlazy/cli@1.2.3","homepage":"https://github.com/dlazy-ai/cli","source":"https://github.com/dlazy-ai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","files.dlazy.com"]},"openclaw":{"systemPrompt":"When this skill is called, run 'dlazy chat --skill product-to-ecommerce-video --prompt ...' for a new task, or 'dlazy chat --project <id> --prompt ...' to continue (discover ids via 'dlazy projects list'). Never pass both --skill and --project."}} ``` ```bash npx @dlazy/cli@1.2.3 <command> ``` ```bash npm install -g @dlazy/cli@1.2.3 ``` ### Technical Analysis The skill instructs the environment to retrieve and execute `@dlazy/cli@1.2.3` from the npm registry. Although the package version is pinned, the project does not include the dependency source, an npm lockfile, a cryptographic integrity digest, a verified artifact signature, or other controls that bind execution to reviewed package contents. Version pinning limits unexpected upgrades but does not independently establish artifact integrity or trustworthiness. The `npx` path downloads and executes the package on demand, while the global installation path places the package persistently in the user's npm environment. npm lifecycle scripts may also execute during installation unless explicitly disabled. The audited project contains only documentation files, so the actual implementation and behavior of the referenced CLI could not be verified within the supplied audit scope. ### Attack Path 1. A user or Agent loads the skill and f ...[truncated 1449 chars]
Remediation
<![CDATA[ ## Remediation Suggestions 1. Vendor and audit the required CLI implementation, or otherwise make the exact reviewed source available with the skill. 2. Supply a lockfile containing npm integrity hashes and verify the resolved package against the expected SHA-512 digest before execution. 3. Use signed release artifacts and verify the publisher identity and signature as part of installation. 4. Avoid global installation. Prefer an isolated, temporary environment with a minimal filesystem view and restricted permissions. 5. Disable npm lifecycle scripts where compatible, such as with `npm install --ignore-scripts`, and separately audit any scripts required for operation. 6. Pin and integrity-lock all transitive dependencies rather than relying only on a top-level semantic version. 7. Restrict the CLI's outbound network access to the explicitly documented service endpoints. 8. Run the CLI as an unprivileged account and never install it with administrator or root permissions. 9. Prevent unnecessary exposure of environment variables, credentials, and unrelated local files to the CLI process. 10. Establish dependency monitoring and repeat the security review before changing the package version or accepted integrity digest. ]]>

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The file is a Chinese-language skill description and instructions, but it does not state that language choice is optional or that the skill is specifically limited to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in can be a locale policy violation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.