Security audit
Security checks for vulnerabilities and agentic risk
This is a plain Markdown ADHD planning skill with no code execution or persistence, but users should treat its medication-related templates as non-medical self-tracking only.
Before installing, understand that this skill is a planning and self-management aid, not clinical ADHD treatment. Use the medication sections only to track observations or prepare questions for a qualified clinician; do not start, stop, skip, or adjust medication based on the skill's templates alone.
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.
- Low-stakes tasks only
- No major decisions
**The key**: Don't judge bad days. They're part of the pattern.
## Tools That Actually Help
The manifest description broadly states that the skill provides planning and executive-function support for ADHD without specifying when it should or should not be invoked. In a manifest file context, this kind of open-ended capability description can overlap with many everyday planning or support requests and lacks negative examples or scope boundaries.
The file includes 'Medication management' as a dopamine-supporting practice and broadly encourages self-directed behavior changes, but it does not include any caution to use medication only as prescribed or to consult a qualified clinician for medication-related concerns. In a mental health/ADHD support skill, omission of that boundary can normalize unsupervised medication adjustment or overgeneralized health advice, which may lead some users to make unsafe decisions.
The medication section includes tracking and 'Tomorrow adjustment needed? Y/N' language without an explicit warning to consult a licensed clinician before changing dose, timing, or regimen. In a mental-health-adjacent ADHD planning skill, users may interpret this as actionable self-management advice and make unsafe medication changes based on subjective daily observations.
No suspicious patterns detected.