The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npm, tar, and npx for environment setup and code validation. Specifically, it uses npm pack and tar to manage type definitions and npx to run development tools like tsc, eslint, and oxlint.
[EXTERNAL_DOWNLOADS]: The skill performs external downloads of the official @cloudflare/workers-types package and retrieves documentation directly from developers.cloudflare.com. These downloads target official Cloudflare resources and are consistent with the skill's primary purpose.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to the ingestion of untrusted data from external documentation and user-provided Workers code.
Ingestion points: Fetches content from developers.cloudflare.com and reads user source code and configuration files.
Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore embedded commands within the fetched external content.
Capability inventory: The agent is authorized to execute shell commands (npm, tar, npx) as part of its review and validation workflow.
Sanitization: There is no mention of sanitizing or validating the content of the external documentation or user code before it is processed by the agent.

workers-best-practices