MyVibe Skills

Publish static HTML, ZIP archive, or directory to MyVibe. Use this skill when user wants to publish web content to MyVibe.

This skill generally does what it claims, but it requires running network-enabled commands, installing npm packages (potentially globally), starting local servers, and writing files in your home and /tmp directories. Before installing or invoking it: 1) Review scripts/utils/auth.mjs to see how access tokens are obtained/stored and where tokens are written; 2) Audit package.json/package-lock.json (and the @aigne dependencies) for any packages you don't trust; 3) Avoid granting a broad/elevated sandbox permission unless you run the skill in an isolated environment (VM or disposable container); 4) Be cautious about allowing global installs (agent-browser) and npx runs — prefer installing required dependencies in an isolated environment under your control; 5) If you need only metadata or simple uploads, consider using a narrower tool that doesn't request global installs or elevated sandbox privileges. If you want, I can inspect auth.mjs (not shown fully) and the remaining truncated files for token storage or other sensitive behavior to refine this assessment.

Type: OpenClaw Skill Name: myvibe-skills Version: 1.0.0 The skill is classified as suspicious due to several high-risk capabilities, even though the explicit intent appears benign. Key indicators include the requirement for `sandbox_permissions=require_escalated` for network access, the instruction to the AI agent to perform a global `npm install -g agent-browser && agent-browser install` in `SKILL.md` and `generate-screenshot.mjs`, and the dynamic execution of `npx http-server` in `generate-screenshot.mjs`. These actions involve downloading and executing external code and modifying the system environment, which introduces significant supply chain and arbitrary code execution vulnerabilities if the external packages or the agent's execution context were compromised. Additionally, the skill makes network requests to a user-configurable `--hub` URL, which could be abused if the agent is tricked into publishing to a malicious endpoint. While these capabilities are plausible for a publishing and screenshotting skill, they represent substantial attack surfaces without clear evidence of intentional malice.