The Agent Skills Directory

[SAFE]: The skill is entirely composed of documentation and templates in Markdown and TypeScript. No malicious patterns or security risks were identified.
[PROMPT_INJECTION]: The instructions in SKILL.md are descriptive and focused on guiding the agent to provide API design assistance. There are no attempts to bypass safety filters or override core instructions.
[DATA_EXFILTRATION]: The skill does not access sensitive local files or perform any network requests. It only references internal files within its own directory for error handling and examples.
[REMOTE_CODE_EXECUTION]: No patterns for downloading or executing remote scripts were found. The skill does not use any package managers or remote fetching tools.
[COMMAND_EXECUTION]: There are no subprocess calls, shell commands, or scripts included in the skill. The only allowed tool is 'Read'.
[OBFUSCATION]: All content is provided in clear text Markdown and TypeScript. No encoded strings, hidden characters, or homoglyphs were detected.

api-contract