The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown-formatted instructions and governance guidelines. There is no executable code, shell scripting, or logic that interacts with the operating system or file system directly.- [PROMPT_INJECTION]: The content does not contain any instructions that attempt to bypass AI safety filters, extract system prompts, or override agent behavioral constraints. The 'Identity' section defines a professional role that is consistent with the skill's stated purpose without using adversarial role-play patterns.- [DATA_EXFILTRATION]: No hardcoded credentials, API keys, or sensitive file paths (such as .ssh or .aws directories) were detected. The skill provides guidance on 'least privilege' and 'data minimization' but does not include any commands to transmit data to external domains.- [REMOTE_CODE_EXECUTION]: There are no patterns involving external package installation, remote script fetching, or dynamic code execution via shell commands. The technical standards provided in the text are for the agent to use when evaluating other work, rather than code to be executed by the skill itself.- [EXTERNAL_DOWNLOADS]: The skill does not reference any external URLs for downloading dependencies, configuration, or payloads. It relies entirely on its internal instructional content.

pharmacy-systems-expert