Vulnerability in Langchain
CVE-2023-29374
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.397, 98.6th percentile (last changed ); unchanged over 30 days. About EPSS.
Affected products
Weakness classification (CWE)
Public exploits and proof-of-concept code
Also mentioned in 4 other repositories (cckuailong/awesome-gpt-security, corca-ai/awesome-llm-security, invariantlabs-ai/invariant, …). These reference the CVE in a list, notes or a scanner and are not exploit code for it.
References
- github.com/hwchase17/langchain/pull/1119 (Patch)
- github.com/hwchase17/langchain/issues/814 (Exploit, Patch, Issue Tracking)
- twitter.com/rharang/status/1641899743608463365/photo/1 (Exploit)
- github.com/hwchase17/langchain/issues/1026 (Issue Tracking)