The Agent Skills Directory

[SAFE]: The skill provides explicit security guidelines for the agent to avoid including secrets, credentials, API tokens, private keys, or personal data in the documentation it generates.
[SAFE]: The documentation framework described (Jotdown) implements a restricted execution environment for content pages. The instructions explicitly prohibit executable or high-risk tags such as <script>, <iframe>, <object>, <embed>, and on* event handlers, reducing the risk of cross-site scripting (XSS) or remote content injection in the rendered documentation.
[SAFE]: The skill references official documentation and decision records from the Jotdown repository on GitHub, which are used to provide context and guidance on project branding and structure.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process repository files (Markdown and JSON). While this involves ingesting external data, the risk is mitigated by the skill's strict formatting rules and the framework's refusal to compile executable code or dynamic expressions found within those files.

authoring