GHSA-p2qj-r53j-h3xj — LangChain Experimental Eval Injection vulnerability

The advisory, in context

langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).

Affected packages

Start with the recorded fix for your release branch. Check your installed version and test compatibility before upgrading. Fixing this advisory does not rule out other vulnerabilities in the release.

langchain-experimental PyPI

Ecosystem versions

From 0.1.17 through 0.3.0 (inclusive)

No fix recorded for this interval.

2 explicitly affected versions

0.3.0, 0.3.0.dev1

View affected-version evidence

{
  "ranges": [
    {
      "events": [
        {
          "introduced": "0.1.17"
        },
        {
          "last_affected": "0.3.0"
        }
      ],
      "type": "ECOSYSTEM"
    }
  ],
  "versions": [
    "0.3.0",
    "0.3.0.dev1"
  ]
}

Set up in your agent.

Investigate in your agent.

LangChain Experimental Eval Injection vulnerability

The advisory, in context

Affected packages

References