ok-plan
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill performs localized file operations (reading from
.ok/objective.mdand writing to.ok/plan.mdand.ok/actions/) to assist with project management and task decomposition. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from
.ok/objective.mdwhich may be user-provided or from external sources. While this represents a potential ingestion point for indirect instructions, the skill's functionality is limited to formatting and planning within a specific directory, posing a low risk. No specific sanitization or boundary markers are defined in the prompt instructions.
Audit Metadata