CVE-2024-1455 json
Billion Laughs Attack leading to DoS in langchain-ai/langchain
published 2024-03-26 2 y ago modified 2026-07-07 4 mo ago also GHSA-q84m-rmw3-4382 , PYSEC-2026-1519 , EUVD-2024-0987
- cvss
- 5.9
- version 3.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.8%
- EPSS 0.8% chance of exploitation in 30 days, percentile 55%
- public exploits
- 0
- none known
Summary
A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading to a denial of service (DoS).
Patch / fix
- pypi langchain-core 0.1.35
- langchain-ai langchain-ai/langchain 0.1.35
- langchain-ai langchain-ai\/langchain 0.1.35
- github.com/langchain-ai/langchain@727d502 commit
- github.com/langchain-ai/langchain#17250 pull request
- github.com/langchain-ai/langchain#19653 pull request
- github.com/langchain-ai/langchain#19660 pull request
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 2 y ago
Exploit prediction
0.76% chance of exploitation in the next 30 days, higher than 55% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- huntr.com https://huntr.com/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.0 | 5.9 | CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H |
| NVD | 3.1 | 5.9 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H |
| OSV | 3.0 | 5.9 | CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H |
| GitHub | 3.0 | 5.9 | CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | langchain-core | <0.1.35 |
0.1.35 |
Affected products
- langchain-ai langchain-ai/langchain
- langchain-ai langchain-ai\/langchain
Classification
- Weakness
-
- CWE-776 Improper Restriction of Recursive Entity References in DTDs
References
-
github.com
/langchain-ai/langchain/commit/727d5023ce88e18e3074ef620a98137d26ff92a3
web, patch
-
github.com
/langchain-ai/langchain/pull/17250
web
-
github.com
/langchain-ai/langchain/pull/19653
web
-
github.com
/langchain-ai/langchain/pull/19660
web
-
huntr.com
/bounties/4353571f-c70d-4bfd-ac08-3a89cecb45b6
web, exploit, third-party-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2024-1455
advisory
-
github.com
/langchain-ai/langchain
package
-
pypi.org
/project/langchain-core
package
-
github.com
/advisories/GHSA-q84m-rmw3-4382
advisory
Sources
- CVE List CVE-2024-1455
- GitHub Advisory GHSA-q84m-rmw3-4382
- NVD CVE-2024-1455
- OSV PYSEC-2026-1519
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.