Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent executive-function support skill with no executable code, but users should be aware that it may reuse planning and time-tracking context across sessions if the host system stores it.
Install only if you want an agent to help structure tasks, plans, reminders, and work sessions. Review the host application's memory and tool permissions first, especially whether it can save task history or time-tracking patterns across sessions; disable those features if you do not want that continuity.
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
### Review & reflection
Use when: at the end of a work session or day.
What it does: captures what got done, what didn't (without judgment), and notes patterns.
## Working with time
The activation guidance is very broad and can trigger on common statements like feeling stressed, unfocused, or overwhelmed, which risks routing ordinary conversations into this skill when the user did not clearly request it. In a support-oriented skill, over-invocation can lead to unnecessary collection of sensitive behavioral context and inappropriate steering of the conversation.
The skill instructs the system to carry forward prior-session context and time-tracking patterns, but it does not clearly require user consent, retention limits, or a privacy notice. Because this skill deals with potentially sensitive mental-health-adjacent and productivity data, silent persistence increases privacy and profiling risk.
No suspicious patterns detected.