The Agent Skills Directory

[SAFE]: The skill consists purely of markdown-based templates and instructional rules for goal-setting and metrics frameworks. Analysis of all files, including the core logic in SKILL.md and the detailed criteria in the rules/ directory, confirms there are no scripts, executable commands, or hidden instructions.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to analyze and structure user-provided organizational goals and metric definitions (ingestion surface), it lacks dangerous capabilities such as shell execution, file writing, or network exfiltration within its own logic that could be exploited via malicious input. The risk remains at the baseline for an AI assistant.

okr-design