CVE-2026-75130

CRITICALPre-NVD 9.09.0—
EchelonGraph scoreHIGH confidence

Score 9.0 from GitHub Security Advisory published 2026-08-18. a secondary CVSS source baseline 9.0; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: epss, ghsa, secondary
Trending — 4 sources updated this week
9.0EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 9.0Exploit: None knownExposed: 0

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

Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim's machine when the agent makes a routine library documentation request.

CVSS v3
9.0
EG Score
9.0(high)
EG Risk
41(Track)
EG Risk 41/100SSVC: Track

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity90% × 45%
Exploitation0% × 40%
Automatability0% × 15%
Action: Routine — remediate on your standard cadence.
EPSS PROB
0%
EPSS %ILE
20%
KEV
Not listed

Published

August 18, 2026

Last Modified

August 19, 2026

Advisory Details (3)

Auto-updated Aug 18, 2026
⚠️ Active exploitation confirmed. No patch confirmed yet.
generic

Context7 2.1.2 Prompt Injection via Custom AI Instructions | Advisories | VulnCheck

https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions
generic🔴 Active Exploitation

Context7 Security: AI Agent Vulnerability Mitigation | Upstash posted on the topic | LinkedIn

https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/
generic🔴 Active Exploitation

ContextCrush: The Context7 MCP Server Vulnerability Hiding in Plain Sight - Noma Security

https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/

Vendor Advisories for CVE-2026-75130(1)

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

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 17× in last 7d / 17× 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. 2026-08-20 09:08 UTCGHSA enrichment
  2. 2026-08-20 04:58 UTCGHSA enrichment
  3. 2026-08-20 00:47 UTCGHSA enrichment
  4. 2026-08-19 20:36 UTCEG score recompute
  5. 2026-08-19 20:36 UTCGHSA enrichment
  6. 2026-08-19 17:04 UTCEPSS rescore
  7. 2026-08-19 16:26 UTCEG score recompute
  8. 2026-08-19 16:26 UTCGHSA enrichment
  9. 2026-08-19 15:19 UTCGHSA enrichment
  10. 2026-08-19 11:05 UTCGHSA enrichment
  11. 2026-08-19 06:55 UTCGHSA enrichment
  12. 2026-08-19 02:45 UTCGHSA enrichment
  13. 2026-08-18 22:32 UTCEG score recompute
  14. 2026-08-18 22:32 UTCGHSA enrichment
  15. 2026-08-18 18:22 UTCEG score recompute
  16. 2026-08-18 18:15 UTCEG score recompute
  17. 2026-08-18 18:14 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-75130?
CVE-2026-75130 is a critical vulnerability published on August 18, 2026. Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions…
When was CVE-2026-75130 disclosed?
CVE-2026-75130 was first published in the National Vulnerability Database on August 18, 2026, with the most recent update on August 19, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-75130 actively exploited?
CVE-2026-75130 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 80.0% of all scored CVEs.
What is the CVSS score of CVE-2026-75130?
CVE-2026-75130 has a CVSS v3 base score of 9.0 (NVD).
How do I remediate CVE-2026-75130?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-75130, 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

Explore the affected products and dependency analysis for CVE-2026-75130

Explore →

Is Your Infrastructure Affected by CVE-2026-75130?

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

Start Free Scan →Browse All CVEs