What is CVE-2026-75130?

CVE-2026-75130 is Context7 2.1.2 Prompt Injection via Custom AI Instructions. The supplied enrichment data classifies it as Injection mapped to CWE-1427 CWE-1427.

Which versions are affected?

Affected product and version evidence is listed in the product table above. Current public advisories should be checked for exact version scope before patch targeting is finalized.

Is there active exploitation?

Active exploitation is not confirmed from current sources for CVE-2026-75130. If exploitation is not confirmed from current sources, teams should document that status and continue monitoring KEV, vendor, and telemetry updates.

No. CVE-2026-75130 is not listed in CISA KEV in the supplied enrichment data. KEV status should be monitored because it can change after initial disclosure or after exploitation becomes publicly confirmed.

Is there a public exploit?

2 public PoC repositories reported; 0 marked weaponized in current dataset. Public exploit or PoC availability should raise triage priority, especially for exposed or business-critical systems.

How can defenders detect it?

Start with web/proxy/WAF logs, application logs, network IDS/IPS, database audit logs where available. Look for vulnerability-class behavior, product errors, suspicious authentication events, exploit probes, and abnormal process activity based only on evidence that applies to the affected product.

How should teams prioritize it?

Prioritize CVE-2026-75130 using CVSS 9, EPSS 0%, KEV status, public PoC status, and asset exposure. Internet-facing, privileged, or business-critical deployments should be handled first.

Are workarounds available?

The supplied mitigation guidance says to apply vendor patches and restrict external exposure until fixed. Fixed-version evidence is listed in the mitigation section above.

Which threat actors are linked publicly?

No public threat actor linkage is confirmed from current sources. Do not attribute exploitation to a threat actor unless the source evidence explicitly supports that linkage.

What should be done in the next 24 hours?

Identify exposed assets running affected vendor/product/version combinations. Prioritize based on EPSS, PoC availability, and external exposure. Search available logs for exploit probes, errors, authentication anomalies, or suspicious child processes matching the vulnerability class. Open remediation tickets with affected assets, owners, evidence status, and detection coverage so decisions are traceable.

criticalInjectionpublic exploit

CVE-2026-75130

CVE-2026-75130 — Context7 2.1.2 Prompt Injection via Custom AI Instructions

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.

Published Aug 18, 2026Updated Aug 18, 2026Sources: NVD, Uptash (CNA), GitHub, GitHub Security Advisory, SOCRadar CTI

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the scoring sources call it.

Exploitation

Exploit code

public exploit, none observed

EPSS

ahead of 0% of scored CVEs

Affects

Uptash

Context7

CVSS base

critical · 2 sources

Remediation

The vendor's own words where we have them.

Upgrade Context7 to a fixed release. Apply vendor patches per advisory and restrict external exposure of the affected component until patched.

First 24 hours

Ordered from the record's own fields — exposure first, because you cannot patch what you have not found.

Identify exposed assets running affected vendor/product/version combinations.
Prioritize based on EPSS, PoC availability, and external exposure.
Search available logs for exploit probes, errors, authentication anomalies, or suspicious child processes matching the vulnerability class.

Affected scope

Vendor, product and version as the advisories word them.

Vendor	Product	Versions	Status
Uptash	Context7	0 to <= 2.1.2	Vulnerable

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Availability

High

Confidentiality

High

Integrity

High

Scope

Changed

Attack Complexity

Low

Attack Vector

Network

Privileges Req

Low

User Interaction

Required

Every base score collected

Sources score independently and disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Source
9	CVSS 3.1	critical	2.3	6	NVD, Uptash (CNA), GHSA
6.4	CVSS 4.0	medium	—	—	Uptash (CNA)

CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H

Weakness & attack patterns

CWE-1427

Inferred from the weakness class — not observed against this CVE.

CAPEC-66 · SQL InjectionCAPEC-7 · Blind SQL Injection

Public exploit

Capability, not use: code existing is a different claim from anyone running it.

Repositories

Detection

Read off the CVSS vector and the weakness class. Starting points, not rules we have tested.

Prioritize edge telemetry for network-reachable Context7.
Monitor for scanner or exploit-pattern traffic after 2 public PoC repositories were reported.

web/proxy/WAF logsapplication logsnetwork IDS/IPSdatabase audit logs

Timeline

What happened to this CVE, newest first — with the readings a source repeats on a schedule counted underneath rather than listed.

2026
Added · CVSS 3.1 9.0 (AV:N)
Aug 18, 2026 · NVD
Initial · CVE published
Aug 18, 2026 · NVD
Added · GHSA-97r6-3rgm-v39r published (medium)
Aug 18, 2026 · GitHub Security Advisory

Source activity

Readings a source repeats on a schedule, counted rather than listed.

2×ModifiedAug 18, 2026 · SOCRadar CTI

References

5 on the record

noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/
Vendor Advisory, NIST, Mitre
www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/
Vendor Advisory, NIST, Mitre
www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions
Vendor Advisory, NIST
nvd.nist.gov/vuln/detail/CVE-2026-75130
NVD
github.com/advisories/GHSA-97r6-3rgm-v39r
Exploit, Third Party Advisory

Elsewhere on this site

Uptashevery CVE for this vendor
Injectionsame class
CWE-1427other pages naming this weakness

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record1

What should defenders know first?

CVE-2026-75130 is Context7 2.1.2 Prompt Injection via Custom AI Instructions, a critical vulnerability affecting Context7 from Uptash. The current evidence does not list it in CISA KEV, and the exploit status is: Active exploitation is not confirmed from current sources for CVE-2026-75130. Public exploit evidence is: 2 public PoC repositories reported; 0 marked weaponized in current dataset. The affected-version evidence is listed in the key facts and affected products tables. Defenders should first verify whether exposed or business-critical assets run those versions, then apply vendor patches or mitigations, restrict reachable attack surface, and preserve logs for detection review. CVSS 9 describes technical severity, while EPSS 0% helps estimate near-term exploit likelihood; neither replaces asset context. Unknown fields should remain explicit in tickets, and threat actor, IOC, victimology, or payload claims should not be added unless a cited source supports them. Monitor CISA KEV, vendor advisories, NVD changes, public PoC repositories, and internal telemetry for update triggers.