CVE-2026-59820

MEDIUMNVD 6.56.5
EchelonGraph scoreMEDIUM confidence

This medium-severity CVE scores 6.5 under NVD CVSS v3. EPSS exploit probability: 0.3%, top 77% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, nvd
6.5
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS: 0%CVSS: 6.5Exploit: NoneExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.7-stable, LiteLLM Skills archive extraction did not sufficiently validate file paths from uploaded skill ZIP archives, allowing an authenticated user with access to LiteLLM LLM API routes or a key whose allowed_routes includes /v1/skills, anthropic_routes, or llm_api_routes to upload a crafted skill archive containing path traversal entries that could be written outside the intended extraction or staging directory. This issue is fixed in version 1.83.7-stable.

CVSS v3
6.5
EG Score
6.5(medium)
EG Risk
EPSS
23.6%
KEV
Not listed

Published

July 8, 2026

Last Modified

July 13, 2026

Advisory Details (4)

Auto-updated Jul 8, 2026
Patch available. Sources: github_commit, github_pr, github_release, github.
github Patch Available

Arbitrary file write via path traversal in Skills archive extraction · Advisory · BerriAI/litellm · GitHub

https://github.com/BerriAI/litellm/security/advisories/GHSA-5jmr-gcrj-2c9q
github_release Patch Available

v1.83.7-stable

Patch available: BerriAI/litellm v1.83.7-stable

https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable
github_pr

[Fix] Harden file path resolution in skill archive extraction

Fix merged in BerriAI/litellm PR #25475 on 2026-04-10 — awaiting tagged release

https://github.com/BerriAI/litellm/pull/25475
github_commit

commit 6a15adcd6413 (BerriAI/litellm)

Fix landed in BerriAI/litellm commit 6a15adcd6413 — awaiting tagged release

https://github.com/BerriAI/litellm/commit/6a15adcd64137d37f73dee76dfe7481f8c2d9196

Vendor Advisories for CVE-2026-59820(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFixed inDependents
litellm0.1.0 ... 1.9.dev0 (1108 versions)1.83.7

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 9× in last 7d / 25× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-07-22 14:08 UTCEPSS rescore
  2. 2026-07-22 14:08 UTCEPSS rescore
  3. 2026-07-21 15:25 UTCEPSS rescore
  4. 2026-07-21 15:25 UTCEPSS rescore
  5. 2026-07-20 17:08 UTCEPSS rescore
  6. 2026-07-19 14:31 UTCEPSS rescore
  7. 2026-07-19 02:29 UTCEPSS rescore
  8. 2026-07-18 10:04 UTCEPSS rescore
  9. 2026-07-16 17:03 UTCEPSS rescore
  10. 2026-07-15 16:57 UTCEPSS rescore
  11. 2026-07-15 16:57 UTCEPSS rescore
  12. 2026-07-15 02:00 UTCEPSS rescore
  13. 2026-07-15 02:00 UTCEPSS rescore
  14. 2026-07-13 22:31 UTCEPSS rescore
  15. 2026-07-13 16:23 UTCEG score recompute 0.40
  16. 2026-07-13 14:08 UTCNVD updateCVSS v3 → 6.5
  17. 2026-07-13 06:13 UTCEPSS rescore
  18. 2026-07-13 06:13 UTCEPSS rescore
  19. 2026-07-12 05:46 UTCEPSS rescore
  20. 2026-07-11 08:27 UTCEPSS rescore
  21. 2026-07-11 08:27 UTCEPSS rescore
  22. 2026-07-09 19:10 UTCEPSS rescore
  23. 2026-07-09 19:10 UTCEPSS rescore
  24. 2026-07-08 19:46 UTCEG score recompute
  25. 2026-07-08 19:44 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-59820?
CVE-2026-59820 is a medium vulnerability published on July 8, 2026. LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.7-stable, LiteLLM Skills archive extraction did not sufficiently validate file paths from uploaded skill ZIP archives, allowing an authenticated user with access to LiteLLM LLM API routes or a key…
When was CVE-2026-59820 disclosed?
CVE-2026-59820 was first published in the National Vulnerability Database on July 8, 2026, with the most recent update on July 13, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-59820 actively exploited?
CVE-2026-59820 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 23.6% percentile likelihood of exploitation in the next 30 days — higher percentiles indicate greater predicted risk.
What is the CVSS score of CVE-2026-59820?
CVE-2026-59820 has a CVSS v3 base score of 6.5 (NVD).
How do I remediate CVE-2026-59820?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-59820, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-59820

Explore →

Is Your Infrastructure Affected by CVE-2026-59820?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.