The Agent Skills Directory

[PROMPT_INJECTION]: The skill does not contain instructions that attempt to override safety filters or manipulate the agent into unauthorized actions. It emphasizes adherence to existing documentation patterns and user-provided instructions.\n- [COMMAND_EXECUTION]: The skill utilizes git for its primary function of maintaining documentation. It incorporates safety guardrails, such as defaulting to collaborative mode and requiring pull requests for all autonomous changes, ensuring human oversight.\n- [DATA_EXFILTRATION]: There is no evidence of unauthorized data transfer. Network-related activities are limited to standard git operations for documentation maintenance.\n- [CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets are present in the skill definition.\n- [EXTERNAL_DOWNLOADS]: References to external domains are restricted to official Mintlify resources (mintlify.com), which are legitimate vendor assets.

doc-author