The Agent Skills Directory

[SAFE]: The skill provides a methodology for qualitative analysis of organizational behavior. It does not include any executable scripts, binary files, or configuration that could affect system security.
[NO_CODE]: No code files (Python, JavaScript, Bash) are present in the skill directory. The logic is entirely contained within Markdown-based instructions.
[PROMPT_INJECTION]: The skill uses terminology like "IRON LAW" to enforce theoretical consistency, but these instructions are scoped to the academic framework and do not attempt to bypass agent safety filters or system-level constraints.
[INDIRECT_PROMPT_INJECTION]: Although the skill processes external scenarios, it has no defined capabilities (such as file system access or network tools) that could be misused if a malicious scenario were provided as input.

grad-sensemaking