The Agent Skills Directory

[SAFE]: The skill follows a well-defined and transparent workflow for situation analysis. All logic is derived from internal instructions and documentation provided within the skill's repository.
[DATA_EXPOSURE]: The skill specifies saving output files to a local directory ({CWD}/kinh-dich-lens/). This is a standard and safe operation for a reporting tool, and no sensitive file paths or credentials are targeted.
[REMOTE_CODE_EXECUTION]: No patterns for downloading, installing, or executing external scripts or packages were detected. The skill relies solely on the LLM's reasoning capabilities and the provided markdown references.
[PROMPT_INJECTION]: The instructions are focused on analysis and do not contain any commands designed to bypass safety filters or override the agent's core identity. The use of structured steps (Step 0 to Step 5) ensures the agent remains on task.
[COMMAND_EXECUTION]: There are no shell commands, system modifications, or privilege escalation attempts within the skill's code or instructions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided topics for analysis. While it lacks explicit input sanitization instructions, the highly structured nature of the I Ching mapping process significantly limits the risk of the agent deviating from its analytical purpose.

kinh-dich-lens