Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Personal Deploy
v1.0.1Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this liv...
⭐ 1· 180·0 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 name/description (deploy to Vercel) matches the instructions: the agent inspects .vercel/, git state, and uses the Vercel CLI. However some requested actions (globally installing the CLI, automatically linking projects in a team/org, and committing every file with `git add .`) are more intrusive than a minimal deploy helper and should be justified explicitly to the user.
Instruction Scope
The SKILL.md instructs the agent to read repository state (.vercel/*, git remotes) which is appropriate, but it also directs potentially dangerous modifications: `npm install -g vercel`, `git add .` then `git commit -m ...` and `git push`, and linking projects without separate confirmation. `git add .`/commit may include secrets or large files; linking can create org-scoped projects. Some steps say 'do not ask for additional confirmation', which reduces user control.
Install Mechanism
The skill is instruction-only (no install spec). That lowers static install risk, but the runtime instructions explicitly tell the agent to run `npm install -g vercel` if the CLI is missing. That is an environment-modifying install triggered at runtime and should be considered a non-trivial action requiring explicit user consent.
Credentials
The skill declares no required env vars or credentials, which fits its use of the local Vercel CLI and git. However the actions it prescribes will access and potentially transmit repository contents (via git push and Vercel deploy). There is no guidance to review commit contents before pushing; that increases the risk of unintentionally publishing secrets or private files.
Persistence & Privilege
The skill does not request always:true, has no install-time persistence, and does not ask to modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) but is not combined with elevated privileges here.
What to consider before installing
This skill looks like a real Vercel deployment helper, but it will ask to modify your repository and environment. Before using it: 1) Do not let the agent run `git add .`/`git commit`/`git push` without first reviewing what will be committed—sensitive files and secrets can be accidentally published. 2) Be aware the skill may run `npm install -g vercel` (a global install) and open a browser for `vercel login`; only proceed in a trusted environment. 3) Linking a project to a team/org can create Vercel projects and enable automatic deploys—confirm that you want that behavior. 4) If you need stricter control, ask the agent to show the exact commands it will run and require explicit approval before any install, link, commit, or push step. Additional information that would raise confidence: an explicit confirmation policy in SKILL.md (e.g., require explicit user approval before install/link/commit/push), and a safer commit workflow (show diffs and files to commit, avoid `git add .`).Like a lobster shell, security has layers — review code before you run it.
latestvk973vbfbmxewwmca3y823bf3vs82t9c6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.