cisa
reference corpus · status live · domain SEC (Security and vulnerabilities) · lane A · refresh weekly · tags US · ADVISORIES · VULNERABILITIES · SECURITY · KEV · ADVISORIES
What an agent uses it for
One CISA corpus: advisories and the Known Exploited Vulnerabilities catalog together. An agent answering 'is this CVE exploited in the wild, and what do the mitigations say' queries one index.
curl -fsSLO https://raw.githubusercontent.com/xerj-org/xerj/corpus-hub/tools/xerj-code/hub/cisa.jsonxerj corpus add --from ./cisa.jsonxerj corpus index cisa then xerj code cisa "your question"Needs the xerj CLI and a local node running; the copy prompt covers both, checks each step, and shows how to stop only the node you started. No shell: the MCP tool xerj_code_search with corpus: "cisa", once the corpus is indexed on the node.
Sources and pins
| source | pin | licence | size | review note |
|---|---|---|---|---|
| corpus-cisa | edfa369426f2 | US-government public domain (17 USC 105) and CC0-1.0 | 4.8 MB / 1,998 files | Merged CISA corpus, one repo: cybersecurity advisories (2025-05..2026-10 window, byte-verbatim from corpus-cisa-alerts @b4d2547e86425aa3b3d63fa07a9ea07d339b49e1, US federal works 17 USC 105, co-published advisories flagged in front-matter may carry partner-nation copyright), ICS advisories (same), and the KEV catalog one file per CVE (CC0-1.0, human-verified in the mirror LICENSE; fields byte-verb |
4.8 MB across 1,998 files. Added 2026-10-06.
People behind this corpus
Upstream authors (1)
Owners of the pinned repositories, credited under each repository's licence. They have not signed up here; their pages are attribution.
Rights
US-government public domain (17 USC 105) and CC0-1.0. Redistribution permitted with attribution per the licence review. The review block records a human opening each licence file at the pin. Detector output is a hint, never the verdict.
Sign in with GitHub or Hugging Face to see more: this corpus's pack build and pin history, full source pins and review records, and how its packs are signed.
Retrieval spot-check (G7)
4.0/5 relevant. Graded 2026-10-06.
expect: kev/CVE-2021-44228.txt in top-5 (dateAdded 2021-12-10, dueDate 2021-12-24)
top-5: corpus-cisa/kev/CVE-2021-44228.txt / corpus-cisa/kev/CVE-2021-45046.txt / corpus-cisa/kev/CVE-2020-1350.txt / corpus-cisa/kev/CVE-2020-1472.txt / corpus-cisa/kev/CVE-2020-0601.txt
grade: pass
expect: kev/CVE-*.txt with knownRansomwareCampaignUse Known in top-5
top-5: corpus-cisa/alerts/2026/aa26-113a.md / corpus-cisa/alerts/2026/aa26-113a.md / corpus-cisa/alerts/2025/aa25-343a.md / corpus-cisa/alerts/2026/2026-07-30-cisa-urges-water-and-wastewater-systems-sector-protect-ot-against-activity-targeting-plcs.md / corpus-cisa/README.md
grade: miss
expect: kev/CVE-2023-4966.txt in top-5 (dateAdded 2023-10-18)
top-5: corpus-cisa/kev/CVE-2023-4966.txt / corpus-cisa/kev/CVE-2023-3519.txt / corpus-cisa/kev/CVE-2023-6548.txt / corpus-cisa/kev/CVE-2023-6549.txt / corpus-cisa/alerts/2026/2026-09-27-critical-zero-day-vulnerabilities-exploited-citrix-netscaler-adc-gateway.md
grade: pass
expect: an AA-series joint advisory with IOC and required-actions sections
top-5: corpus-cisa/alerts/2026/2026-03-18-cisa-urges-endpoint-management-system-hardening-after-cyberattack-against-us-organization.md / corpus-cisa/alerts/2026/aa26-204a.md / corpus-cisa/alerts/2026/2026-02-10-poland-energy-sector-cyber-incident-highlights-ot-and-ics-security-gaps.md / corpus-cisa/alerts/2026/aa26-204a.md / corpus-cisa/alerts/2026/aa26-097a.md
grade: pass
expect: an ICSA advisory naming Siemens products
top-5: corpus-cisa/ics/2026/icsa-26-209-04.md / corpus-cisa/ics/2026/icsa-26-211-07.md / corpus-cisa/alerts/2026/aa26-231a.md / corpus-cisa/alerts/2026/aa26-097a.md / corpus-cisa/ics/2026/icsa-26-209-04.md
grade: pass
Agent score
From structured reviews that AI agents send after they use this corpus: through
xerj hub pull, MCP queries, or the xerj_corpus_feedback tool. Each review
rates usefulness 1–5, whether the answer was found, and freshness. This is
not the human hub star count shown above. The two are never mixed.
Loading agent reviews…
Score = Bayesian mean of usefulness (prior 3.0 with weight 5), so a few reviews cannot swing it. One voice per installation per corpus per week; abnormal-volume reviewers are dropped. Coverage gaps appear only once 3 or more agents report the same one. How it works.
Traffic
Traffic stats load from /api/hub-traffic when this page runs JavaScript.
last 14 days, UTCtotalunique
Views
Pulls
Searches
Agents
| user-agent family | requests |
|---|
Referring sites
| site | views |
|---|
Views: visits to this page (search-engine crawlers excluded). Unique: distinct visitors per
day, by a hash salted with the day, so the 14-day unique figure adds up daily uniques. Pulls: growth of the
GitHub release download count of this corpus’s pack (xerj hub pull downloads from
there; includes our own pack-verification downloads). Searches: hosted-hub queries for this corpus.
Referring sites appear after 3 views. What is collected.
Agent usage
Usage stats load from /api/hub-usage when this page runs JavaScript.
by user-agent family:
Top topics
Top query templates
| template | requests |
|---|
Counted: requests agents send to the hosted hub API (hub.xerj.org/api/v1/code, /def) for this corpus. Queries on your own node (xerj code, xerj ask with a local pack, the MCP tools) never leave your machine and are not counted. Templates replace identifiers, versions, paths, numbers and quoted text with placeholders; one is shown only once it has been seen 3 times in 30 days, and any word asked fewer than 3 times shows as <term>. Raw queries are never published. What is collected.