The Agent Skills Directory

[SAFE]: The skill is composed of purely informational and instructional Markdown files. It does not contain any scripts (Python, JavaScript, shell) or binaries that could be executed in the environment.
[PROMPT_INJECTION]: The instructions clearly define a role-playing persona for psychological support. There are no patterns suggesting attempts to bypass safety filters, extract system prompts, or override agent constraints.
[EXTERNAL_DOWNLOADS]: The documentation includes links to official psychological organizations and related GitHub repositories for reference. These links are contextually relevant to the skill's purpose and do not involve remote code execution or suspicious script piping.
[DATA_EXFILTRATION]: No sensitive file paths, credential markers, or suspicious network operations were detected. The skill does not request tools that would enable data movement.
[COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or dynamic context injection patterns (e.g., the !command syntax) present in the instructions.

adler-perspective