The Agent Skills Directory

[DATA_EXFILTRATION]: The skill is designed to read and analyze environment configuration files, including .env, .env.local, .env.development, and .env.production. These files typically contain sensitive secrets such as API keys, database credentials, and authentication tokens. While this access is the primary purpose of the skill, the agent will have full read access to these sensitive local files to perform its validation tasks.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from local configuration files and source code to generate reports and new validation files, creating a surface for indirect prompt injection.
Ingestion points: The skill reads contents from .env files and application source code files (.ts, .tsx, .js, .jsx) to identify variable usage.
Boundary markers: The instructions do not specify the use of delimiters or specific guidance to the agent to ignore potentially malicious instructions that might be embedded within the files being scanned.
Capability inventory: The skill has the capability to write to the local file system, specifically creating or updating .env.example and env.ts validation files.
Sanitization: No explicit sanitization or validation steps are defined for the content extracted from user files before it is interpolated into reports or generated code.
[EXTERNAL_DOWNLOADS]: The skill references the installation of the @t3-oss/env-nextjs and zod packages. These are standard, well-known libraries in the developer community for managing environment variables and schema validation.

env-config-validator