Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
wanjie-openclaw-video
v1.0.0Generate high-performance Veo videos from natural language prompts with automatic dependency handling, timeout recovery, and continuous background monitoring.
⭐ 0· 12·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The code's behavior (reading ~/.openclaw/openclaw.json for an apiKey and calling https://maas-openapi.wanjiedata.com) is consistent with a Veo/MaaS integration, but the skill metadata declares no required config paths or credentials. The skill uses the user's OpenClaw API key from a config file rather than an explicit environment variable, which should have been declared.
Instruction Scope
SKILL.md promises periodic background monitoring every 5 minutes and 'deploys Windows Task Scheduler OpenClaw_Veo_Monitor', but the provided code contains no installer or scheduler-creation logic. The runtime does read the user's config file and writes logs/results to the skill folder, spawns detached Python processes, auto-installs 'requests' if missing, and opens any URL returned by the remote API — actions not fully described or declared in the manifest.
Install Mechanism
There is no install spec (instruction-only), but the included Python helper can run pip install at runtime to install 'requests'. This is a common pattern but still results in network package installation during execution rather than at explicit install time.
Credentials
The skill reads a sensitive config file (~/.openclaw/openclaw.json) to extract an apiKey and uses it to authenticate requests to a third-party API. That credential access is functionally justified, but it is not declared in requires.env or required config paths. Also, the skill will automatically open the first URL returned by the service in the user's default browser, which could be unexpected or unsafe.
Persistence & Privilege
The skill does not set always: true and does not modify other skills' configurations. However, hooks.js spawns detached background worker processes and the code writes lock/log/result files under model/scripts; SKILL.md's claim of installing a Windows scheduled task is not implemented in the code — an inconsistency to clarify. Detached processes plus auto-dependency installation increase the operational footprint compared with a purely stateless skill.
What to consider before installing
Things to consider before installing:
- This skill will read ~/.openclaw/openclaw.json and use the apiKey it finds there to call https://maas-openapi.wanjiedata.com. If you don't want the skill to have access to that key, do not install it or inspect/modify the code to accept an explicit, limited key.
- The manifest does not declare the required config path or credential, but the code uses it — ask the author to declare required config paths or change to use a named env var so you can control which key is used.
- The skill can auto-install Python packages at runtime (requests) and spawns detached background Python processes. If you prefer to control installs and processes, review and run the code manually in a sandboxed environment first.
- The worker opens the first URL returned by the remote service in your browser automatically. That URL may be attacker-controlled if the remote service is compromised; consider disabling automatic opening or inspect the returned URL before clicking.
- SKILL.md claims a Windows scheduled task will be created; no code does that. Confirm with the author whether additional install steps are needed or whether documentation is stale.
- If you decide to proceed, run the skill in an isolated environment (VM/container/user account) and audit ~/.openclaw/openclaw.json contents and permissions. Ask the developer to (a) explicitly declare required config paths/credentials in the manifest, (b) avoid automatically opening external URLs, and (c) provide a reproducible installation mechanism for any background scheduler they claim to create.hooks.js:11
Shell command execution detected (child_process).
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk97a1zmb2e1f22k72pnn4w9jq184j3ht
License
MIT-0
Free to use, modify, and redistribute. No attribution required.