The Agent Skills Directory

[SAFE]: The skill provides standard configuration and implementation guidelines for common JavaScript development tools (ESLint, Prettier, Jest, Vitest, Vite, Rollup). No malicious code, obfuscation, or unauthorized data access patterns were identified.
[COMMAND_EXECUTION]: The skill references standard package manager commands (npm, yarn, pnpm) and build/test scripts (npm test, npm run build) within its guidelines and CI/CD examples. These are standard practices for JavaScript project maintenance.
[EXTERNAL_DOWNLOADS]: The CI/CD reference documentation includes official GitHub Actions (actions/checkout, actions/setup-node). These are well-known, trusted resources for development workflows.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a vulnerability surface where it ingests untrusted data from project configuration files to provide recommendations.
Ingestion points: .eslintrc., jest.config., and package.json (as specified in SKILL.md triggers).
Boundary markers: Absent; the skill does not use specific delimiters or warnings to ignore instructions embedded in the project files.
Capability inventory: Recommends and demonstrates shell commands for linting, testing, and building (e.g., npm ci, npm test, npm run build in REFERENCE.md).
Sanitization: Absent; the skill does not explicitly filter or validate the content of the configuration files before using them to guide its responses.

javascript-tooling