Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, querying metrics, debugging a deployed app on Vercel (errors, 5xx responses, timeouts, slow routes, or a single failing request), managing domains, managing feature flags with vercel flags, reviewing security checks or Security Review vulnerabilities with vercel security, or interacting with the Vercel platform from the command line. Use the vercel-tracing skill instead for `vercel traces` span search, trace inspection, and sampling rules, or for OpenTelemetry setup.
95%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Decisive route: the skill's decision tree routes "Alerts, usage, contracts, billing purchases, tokens, telemetry, or CLI upgrades" to `references/platform-ops.md` (line 148), which indicates the CLI can perform billing purchases. A purchase is a direct financial operation. The referenced file was not supplied, so the operational detail is thin, and the recall-first override favors counting this route. Direct-operation control: the skill documents `vercel login` (line 125) and states that commands can require login or team SAML re-authentication (line 119). That is service-side authentication gating the CLI session, which the rubric accepts as a qualifying access control. Agent-followed warnings in lines 105 and 176 (non-interactive flags, `--yes`) do not count as controls. Because a direct operation has service authentication, the tier is medium rather than high. Other routes (deployments, env vars, domains, `vercel api`) are not financial operations.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required debugging workflow runs `vercel logs` and `vercel logs requests`, which return runtime log lines and request records that include attacker-controllable request data (paths, query strings, user agents), so an outside requester can get text into results the agent reads without choosing a specific item.
vercel/vercel-plugin
8a9039d
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.