Security context

What an agent needs to avoid regressing past fixes and find the next vuln in this repo.

zylon-ai/private-gpt

              main @ 4cca7d0
            

Fixes

CVEs

HIGH

Peak severity

0.0%

Coverage

Highlights

Remote Code Execution: 1 prior fix. Scrutinize any change in this area.

private_gpt/components/llm/custom/sagemaker.py: most-fixed (1 issue). Treat as high-risk during review.

1 high-severity fix in this history; regressions here are high-impact.

Recurring patterns

The bug types that recur here, drawn from past fixes, not open vulnerabilities.

Remote Code Execution: The integration parsed AWS Sagemaker LLM endpoint responses using Python's native `eval()` function, allowing any compromised or manipulated LLM response payload to execute arbitrary code within the host context.