Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Auto Midjourney
v0.1.2Automate Midjourney Alpha web image generation from Claude using the authenticated https://alpha.midjourney.com session. Use this skill whenever the user wan...
⭐ 0· 80·1 current·1 all-time
by@standed
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The name/description match the implementation: the repo submits Midjourney Alpha web 'imagine' jobs and uses browser/CDP for verification. However the registry metadata lists no required environment variables or primary credential while SKILL.md and the scripts require a full authenticated cookie (MJ_COOKIE) and channel ID (MJ_CHANNEL_ID). That omission is an incoherence: a skill that acts on behalf of a logged-in web session legitimately needs those values and should have declared them.
Instruction Scope
Runtime instructions explicitly tell the agent to read .env or shell vars for the full authenticated Cookie header, infer user_id from the cookie, call /api/submit-jobs and /api/user-mutable-state, attach to a live Chrome session via CDP/Playwright, and download/convert assets. Those actions are within the stated purpose but involve highly sensitive credentials and the ability to perform actions as the user — the SKILL.md gives the agent broad discretion to use the cookie and browser session, which increases risk if misused.
Install Mechanism
The skill is marked instruction-only (no install spec), yet the repo includes package.json/package-lock and Python + Node scripts that expect 'playwright-core' and Python runtime. Users will need to run npm install and install/launch browsers and Python deps manually; the absence of an explicit install spec in the registry is an inconsistency that can lead to surprise (Playwright can download browsers and has network/exec behavior).
Credentials
SKILL.md requires MJ_COOKIE (full authenticated Cookie header) and MJ_CHANNEL_ID as required configuration and lists other optional tokens (MJ_METRICS_TOKEN, MJ_USER_ID, MJ_BROWSER_BACKEND). Requesting a full session cookie is proportionate to the stated functionality but is high-sensitivity and MUST be declared in the registry metadata — its omission is a serious mismatch. The number of env settings is reasonable for web automation, but the required sensitive credential was not surfaced in the declared requirements.
Persistence & Privilege
The skill does not request 'always: true' and does not attempt to modify other skills or global agent settings. It runs local scripts and writes downloads to local directories, which is expected for this use case.
What to consider before installing
Do not install or run this skill until you accept the risk of supplying a full authenticated Midjourney web cookie and channel ID to local scripts. Key points to consider:
- The registry metadata omitted required credentials: SKILL.md and the code require MJ_COOKIE (the full authenticated Cookie header) and MJ_CHANNEL_ID. A full cookie allows the code to act as you on the Midjourney web app — treat it like a password.
- The repo contains Python and Node scripts (Playwright dependency). You will need to run npm install and provide a Python runtime; Playwright can download browsers and execute code that interacts with remote sites and local files.
- If you proceed, run the code in an isolated environment (dedicated VM/container) and avoid using your primary Midjourney account. Prefer a disposable/test account if possible.
- Inspect the key scripts (mj_alpha.py, mj_browser.*, run_imagine.py, mj_doctor.py) yourself or have a trusted developer review them; verify they do not leak your cookie to third-party endpoints. The references mention telemetry endpoints (proxima.midjourney.com) — the skill says it doesn't need them, but review the runtime behavior.
- Corrective action: ask the publisher/registry to update the skill metadata to explicitly declare the required env vars and primary credential, and include a clear install spec and minimal required commands. If that is not fixed, treat the omission as a red flag and be cautious.scripts/mj_playwright_bridge.mjs:140
Dynamic code execution detected.
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.
browser-automationvk97fvz7aec50035rjzs5ztqg9x83b8j5image-generationvk97fvz7aec50035rjzs5ztqg9x83b8j5latestvk97fvz7aec50035rjzs5ztqg9x83b8j5midjourneyvk97fvz7aec50035rjzs5ztqg9x83b8j5promptingvk97fvz7aec50035rjzs5ztqg9x83b8j5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.