> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jaasskills.com/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

<AccordionGroup>
  <Accordion title="Does the registry execute skill code?">
    No. The registry stores, indexes, and serves packages; the guardrails service statically scans files and never executes anything either. Running a skill is the caller's own runtime's responsibility.
  </Accordion>

  <Accordion title="Can I lower a Level 1 guardrail to WARN for my tenant?">
    No — Level 1 is mandatory and enforced by the guardrails service itself, not by caller configuration. Only Level 2–4 checks are configurable, and only Level 2 is on by default.
  </Accordion>

  <Accordion title="What happens to WARN findings — are they stored anywhere queryable?">
    They're recorded as `guardrail_warning_ids` on the immutable publish audit event, not in a separate scan-result store — a tenant audits warning trends from the audit log itself.
  </Accordion>

  <Accordion title="Why does a private skill 404 instead of 403 for an unauthorized caller?">
    So the API never reveals that a private skill exists to someone who can't see it. A 403 would leak existence; a 404 looks identical to "there's nothing here."
  </Accordion>

  <Accordion title="Can a custom rule call out to an external API to check a value?">
    No — every rule, catalog or custom, must be evaluable fully offline from the package's own files. This is a hard design constraint of the guardrails service, not a current limitation.
  </Accordion>
</AccordionGroup>