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.
{
"cwe_ids": [
"CWE-94"
],
"github_reviewed_at": "2023-08-23T13:22:25Z",
"github_reviewed": true,
"nvd_published_at": "2023-08-22T19:16:36Z",
"severity": "CRITICAL"
}