Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Publisher · GitHub organization

elastic

github.com/elastic ↗Last audit 31 Oct 2026

elastic publishes 9 agent skills on the atlas: 5 SAFE, 1 CAUTION, 3 BLOCK, with a mean score of 76/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “elastic: skills and MCP servers”. Retrieved 31 Oct 2026. https://modelsatlas.com/orgs/elastic
Listings
9

0 MCP servers · 9 skills

Mean score
76 / 100

mean of the audit scores

Findings
63

across all listings

Stars
5.4K

on the listed repositories

✓SAFE 5!CAUTION 1✕BLOCK 3

Everything elastic publishes here

Most stars first · stamps show the audited version

kibana-alerting-ruleselastic/agent-skills
Skill ★ 603
✓SAFEB · 89 · 31 Oct 2026
kibana-anomaly-detectionelastic/agent-skills
Skill ★ 603
✓SAFEB · 89 · 31 Oct 2026
kibana-dashboardselastic/agent-skills
Skill ★ 603
✓SAFEB · 89 · 31 Oct 2026
kibana-auditelastic/agent-skills
Skill ★ 603
✕BLOCKF · 51 · 31 Oct 2026
elasticsearch-esqlelastic/agent-skills
Skill ★ 602
✓SAFEB · 89 · 28 Oct 2026
elasticsearch-onboardingelastic/agent-skills
Skill ★ 602
!CAUTIONB · 89 · 28 Oct 2026
kibana-agent-builderelastic/agent-skills
Skill ★ 602
✓SAFEB · 89 · 29 Oct 2026
Skill ★ 602
✕BLOCKF · 51 · 29 Oct 2026
cloud-access-managementelastic/agent-skills
Skill ★ 594
✕BLOCKF · 51 · 20 Oct 2026

Questions

Are elastic's skills safe to install?
Of 9 listings, 5 are SAFE, 1 CAUTION and 3 BLOCK, with a mean score of 76 out of 100. That is an average over separate audits: check each listing's own stamp before installing.
What does this page tell me about elastic?
It collects every skill and MCP server on the atlas whose source lives under github.com/elastic, with each one's verdict. It says nothing about who runs the organisation, and publisher identity is not verified here.
Can a publisher change its verdicts?
No. Each verdict comes from reading the source at a named commit. If a finding is wrong, report it with your reasoning on the listing's page and it is re-audited; the correction is public.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.