Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Video Proof
v1.0.1Record video proof of implemented features after coding tasks complete. Use when a coding agent finishes work and needs to visually verify and demonstrate th...
⭐ 0· 400·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (record video/screenshot proof) match the included scripts (record-proof.js, api-proof.js) and the reference docs. The scripts implement UI walkthrough recording (Playwright) and API request checks, which is exactly what the skill claims to do.
Instruction Scope
SKILL.md and the scripts require you to provide a start_command (any shell command) or point to an already-running server and instruct the agent to produce artifacts and commit them. Allowing arbitrary start_command is necessary for the stated purpose (to start diverse stacks), but it also means the skill will run whatever command the agent or user supplies — verify the start_command and proof-spec before running, and avoid using secrets or production services in a recording run.
Install Mechanism
There is no platform package installer in the registry spec, but the included scripts/setup.sh installs npm packages (playwright, yaml), runs npx playwright install and may attempt to call system package managers (apt-get, brew, dnf, pacman) to install ffmpeg. This is expected for Playwright/video work but is invasive: it modifies (or creates) package.json, downloads node modules and browser artifacts, and may use sudo to install system packages.
Credentials
The skill declares no required env vars or credentials (ok). The scripts spawn the start_command with an env that inherits process.env, and setup.sh runs system package installers — running the skill in an environment with sensitive environment variables or secrets could expose them if the started process or agent-written start_command leaks them. The skill itself does not request unrelated cloud creds or tokens.
Persistence & Privilege
The skill is not forced-always-enabled and does not attempt to modify other skills or system-wide agent settings. It does persist artifacts into a local output directory by design. Autonomous invocation is allowed by default (platform behavior) but not combined with other elevated privileges here.
Assessment
This skill appears to do what it says: it launches a server (via a start_command you provide), uses Playwright to record screen/screenshot/console logs, and writes proof artifacts. Before running: (1) review scripts/setup.sh because it will install node modules, download Chromium via npx playwright and may prompt for sudo to install ffmpeg — run it in a dev VM or container if you want isolation; (2) carefully review any proof-spec.yaml/start_command the agent will use — the skill will execute that shell command as-is, so do not let an untrusted agent choose a start_command or point it at production services; (3) avoid including secrets or production credentials in environment or repo paths used during recording, and review produced artifacts before committing (screenshots, logs, or API responses can include sensitive data); (4) if you need stricter control, run the scripts manually under an isolated user/container and inspect package.json changes and installed binaries first.Like a lobster shell, security has layers — review code before you run it.
latestvk9710t1855r6jg001tyqmx5nfh81w8k3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.