uncertainty-imaging
Renamed to /model-assessment in v6 (removed in v7).
How do I install this agent skill?
npx skills add https://github.com/aperivue/medsci-skills --skill uncertainty-imagingIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill is a reporting-rigor gate for medical-imaging models, focusing on uncertainty quantification and out-of-distribution detection. It uses a deterministic Python script to audit a JSON manifest. The analysis identifies a minor surface for indirect prompt injection because the skill processes external data (the manifest), but it uses standard library JSON parsing and does not exhibit malicious patterns.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
/uncertainty-imaging was renamed to /model-assessment in v6.0; this redirect is removed in v7.
Run /model-assessment now, passing the same arguments the user gave /uncertainty-imaging.
Start at /model-assessment Part C, Phases 10–11 (uncertainty, OOD guard, selective prediction).
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/aperivue/medsci-skills/uncertainty-imaging">View uncertainty-imaging on skillZs</a>