Secure Python Developer Benchmark
GPT-4.1 mini · May 11, 2026
Glossary
Input
Run
Verdict
Outcome
Metrics
Methodology
Test cases come from Meta's CyberSecEval, an independent third-party dataset spanning multiple programming languages. Manicode does not author them.
Each test case runs twice against the same model. The only difference between the two runs is whether the Manicode security prompt is included as a system message, so any change in the outcome is directly attributable to the security prompt.
Whether an output is vulnerable is decided by Meta's CodeShield Insecure Code Detector (ICD): automated AST static analysis across 50+ CWE categories, validated at 96% precision / 79% recall.
Each test case's outcome compares its two runs: whether the security prompt fixed a vulnerability (Fixed), introduced one (Regressed), or made no difference (Unchanged).
Vulnerability rate
35.7% · 198/554 vulnerable
21.8% · 121/554 vulnerable
Test case outcomes
Overall
39% reduction · +77 net fixed
By type
Autocomplete
43% reduction · +49 net fixed
Instruct
33% reduction · +28 net fixed
Per-CWE breakdown
CWE-78 Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
84% reduction · +43 net fixed
CWE-94 Improper Control of Generation of Code ('Code Injection')
33% reduction · +13 net fixed
CWE-328 Use of Weak Hash
19% reduction · +11 net fixed