CVE Intelligence
Medium File handling

CVE-2026-118667 — LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requests

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From langgraph-sdk 0.4.0 until 0.4.6, and from langgraph 1.2.3 until 1.2.14 when RemoteGraph v3 streaming uses an affected langgraph-sdk version, the synchronous and asynchronous v3 stream get_tree and _fetch_state helpers interpolate caller-controlled assistant_id and thread_id values into authenticated GET request paths without using _quote_path_param. Relative path segments can therefore be normalized into another readable path on the configured server while retaining authentication headers. This issue is fixed in langgraph-sdk 0.4.6 and langgraph 1.2.14.

Published Oct 28, 2026 · Updated Oct 29, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP, GitHub Security Advisories · CNA: GitHub_M

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • EPSS 0.4% (30-day exploitation probability)+5
  • Technical severity (medium)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

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

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
0.39%
ahead of 34% of scored CVEs · Oct 29, 2026
Affects
Langchain-ai
Langgraph and 1 more
CVSS base
4.3
Medium · 3 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
None
none · proof-of-concept · active
Automatable
No
can an attacker script the kill-chain steps
Technical impact
Partial
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

  • Pip Langgraph-sdk: fixed in version 0.4.6 — github.com (GitHub Security Advisories)
  • Pip Langgraph: fixed in version 1.2.14 — github.com (GitHub Security Advisories)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Langchain-ai Langgraph, Langchain-ai Langgraph-sdk, Pip Langgraph…).
  2. Apply the fixed version or the patch documented under Remediation.
  3. Search available logs for exploit probes matching the vulnerability class (file handling), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Langchain-ai Langgraph version >= 1.2.3, < 1.2.14 Vulnerable CVE Program (cve.org) e CISA ADP
Langchain-ai Langgraph-sdk version >= 0.4.0, < 0.4.6 Vulnerable CVE Program (cve.org) e CISA ADP
Pip Langgraph ≥ 1.2.3 and < 1.2.14 Vulnerable GitHub Security Advisories
Pip Langgraph-sdk ≥ 0.4.0 and < 0.4.6 Vulnerable GitHub Security Advisories

Attack characteristics

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

Attack vector
Network
Attack complexity
Low
Privileges required
Low
User interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
None
Availability
None

Every base score collected

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

ScoreVersionSeverityExpl.ImpactScored by
4.3 CVSS 3.1 Medium 2.8 1.4 security-advisories@github.com via NIST National Vulnerability Database
4.3 CVSS 3.1 Medium — — GitHub, Inc. via GitHub Security Advisories
4.3 CVSS 3.1 Medium — — GitHub_M via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N (score shown at the top: security-advisories@github.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-22 · Path Traversal

Other CVEs with this weakness →

Detection

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

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
  • Monitor file creation in web directories and paths with traversal sequences (../).
web/proxy/WAF logsnetwork IDS/IPSfile integrity (FIM)endpoint telemetry (EDR)

Timeline

What happened to this CVE, newest first.

  • 2026
  • SSVC assessment updated
    Oct 29, 2026 · CVE Program (cve.org) e CISA ADP
  • Source status changed · Received → Awaiting Analysis
    Oct 29, 2026 · NIST National Vulnerability Database
  • Fix documented
    Oct 28, 2026 · GitHub Security Advisories
  • Affected products added · pip/langgraph-sdk, pip/langgraph
    Oct 28, 2026 · GitHub Security Advisories
  • Affected products added · langchain-ai/langgraph, langchain-ai/langgraph-sdk
    Oct 28, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 28, 2026
  • CVSS changed · 4.3
    Oct 28, 2026 · NIST National Vulnerability Database
  • Source status changed · → Received
    Oct 28, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 28, 2026 · Alertas do Telegram
  • CVE published
    Oct 28, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

  • 2× References added · Oct 28, 2026 – Oct 28, 2026
  • 1× Official description updated · Oct 28, 2026 – Oct 28, 2026

References

6 on the record

Elsewhere on this site

Langchain-ai
every CVE for this vendor
File handling
same class
CWE-22
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-115883 LangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite stores 6d
  • CVE-2026-115885 LangGraph CLI prints the registry push token in `langgraph deploy --verbose` output 6d
  • CVE-2026-104873 LangGraph SDK custom auth silently ignores actions= on resource decorators 28d
  • CVE-2026-71433 LangGraph: Namespace prefix matching crosses segment boundaries in Postgres and SQLite stores Aug 6, 2026
  • CVE-2026-14742 langchain-ai langgraph Task Result Cache _cache.py _freeze weak hash Jul 5, 2026
  • CVE-2026-48775 LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loading Jun 16, 2026

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 record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-118667 is "LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requests", rated Medium. It affects Langgraph (Langchain-ai); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 4.3 describes technical severity. EPSS 0.39% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.