NIST deprecates RSA-2048 from 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
CRITICAL severity

langchain vulnerable to arbitrary code executionGHSA-7gfq-f96f-g85j

CRITICALFix: langchain-ai/langchain#10252

GHSA-7gfq-f96f-g85j is a critical-severity (CVSS 9.8) Code Injection vulnerability in langchain. 2 public exploit or proof-of-concept references are indexed, so weaponization risk is real. A fix is available for langchain — see the affected versions and patch details below.

Also known asCVE-2023-36281PYSEC-2023-151
Published
Updated
Affected
1 pkg
Patched
1 / 1
Exploits
2 known
Exploitation data as of Nov 11, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

Proof-of-concept exploit code exists

  • CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
  • A successful exploit gives an attacker total control of the affected component, not partial access.

Exploitation and automatability from CISA’s SSVC triage for GHSA-7gfq-f96f-g85j.

EPSS Exploitation Probability

via FIRST.org ↗
3.4%probability of exploitation in next 30 days
Lower Risk-0.03%
Lower risk than most CVEs89th percentile — riskier than 89% of all scored CVEsHighest risk
0.00%26.7%53.4%80.1%62.2%3.4%May 26Sep 26Nov 26

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

Where this sits among everything scored

Real-World Exposure

1 pkg affected
🐍langchain

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via the via the a json file to the load_prompt parameter. This is related to __subclasses__ or a template.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIlangchainall versions0.0.312pip install --upgrade 'langchain==0.0.312'

Affected Products

1 product · 1 configurations
Application
langchainlangchain
1 version
0.0.171
Exploits & PoCs
2

Research use only. For defensive security, authorized penetration testing, and academic research only. Never execute exploit code against systems without explicit written authorization.

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for langchain, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update langchain to 0.0.312 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-7gfq-f96f-g85j is resolved across your whole dependency graph.

  3. Workarounds

    Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.

Frequently Asked Questions

An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via the via the a json file to the `load_prompt` parameter. This is related to `__subclasses__` or a template.
O3 Security · Impact-Aware SCA

Is GHSA-7gfq-f96f-g85j in your dependencies?

Find it across PyPI, including transitive dependencies.

GHSA-7gfq-f96f-g85j: langchain RCE — Fixed in 0.0.312