GPU VulnDB

Database/AI/ML frameworks & serving

LangChain (`load_prompt`): Arbitrary code execution from a JSON prompt file

CVE-2023-36281AI/ML frameworks & servingcurated

Impact

Arbitrary code execution from a JSON prompt file

Who can reach it

Customer-supplied prompt file

What to do

Upgrade; prompt files are executable content

References

This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.