The Agent Skills Directory

Security Best Practices: The instructions recommend verifying the Authorization header against a CRON_SECRET environment variable. This is a standard security practice to ensure that only authorized services can trigger scheduled tasks.\n- Trusted Documentation References: The skill references official documentation and sitemaps from a well-known service provider, which provide relevant context for the skill's intended use case.\n- Indirect Prompt Injection Surface: The skill is designed to interact with configuration files, which presents a surface for potential instruction injection.\n
Ingestion points: Metadata specifies vercel.json and apps/*/vercel.json as ingestion points.\n
Boundary markers: The instructions do not define specific delimiters or warnings for these files.\n
Capability inventory: The skill provides logic for editing configuration files and interacting with CLI tools like vercel logs.\n
Sanitization: No explicit sanitization or validation steps are mentioned for the external content of the configuration files it processes.

cron-jobs