The Agent Skills Directory

[SAFE]: The skill's primary function is to act as a technical reference. The instructions and code samples are entirely consistent with the stated goal of secure software implementation.- [PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety guidelines, leak system prompts, or override core agent behavior. It employs standard role-playing constraints for a technical assistant persona.- [COMMAND_EXECUTION]: The documentation mentions CLI tools like Docker and kubectl for deployment. These are presented as educational examples for the user's codebase. The skill contains a specific 'SAFETY GUARD' that requires confirmation before any production-impacting actions are proposed or taken.- [CREDENTIALS_UNSAFE]: Placeholders such as "<jwt_token>", "YOUR_API_KEY_HERE", and "...abc123" are used in examples. No real secrets, tokens, or private keys are exposed within the skill files.- [EXTERNAL_DOWNLOADS]: The skill references established technology platforms and official package registries (npm, PyPI) as part of standard build and deployment workflows. These references are safe and consistent with the skill's purpose.

fullstack-guardian