The Agent Skills Directory

Credential Management: The skill involves the use of Vercel OIDC tokens and environment configuration files (.env.local) for authentication. It emphasizes secure handling by explicitly instructing against printing tokens in logs, pasting them into source code, or committing environment files to version control, which aligns with industry best practices for secret management.
Dynamic Command Execution: The skill utilizes the Vercel CLI via vc env run -- sh -c ... to inject environment variables into browser automation workflows. This represents a low-severity dynamic execution pattern that facilitates the secure transfer of short-lived credentials to automated tools using a predictable template.
Indirect Prompt Injection Surface: The skill is designed to interact with external Vercel deployments and process their content via vc curl or agent-browser. This introduces a potential surface for indirect prompt injection if an attacker-controlled deployment contains malicious instructions intended to influence the agent.
Ingestion points: Target deployment URLs and the resulting HTTP or browser response data (referenced in SKILL.md).
Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore embedded content within the responses.
Capability inventory: The skill possesses network interaction capabilities through vc curl and browser automation via agent-browser.
Sanitization: No specific filtering or sanitization steps are provided for the content received from the deployments.

access-protected-vercel-deployment