Author test
jev-sec-bench
Evaluate injection and vulnerable-code detection
How this project uses Jev
- Input
- Public-corpus messages and paired code samples
- Jev decides
- Whether content is an injection or poses a security risk
- Code executes
- A Go evaluator computes metrics and saves per-sample results
Evidence and limitations
The author records 662 injection samples and 200 code pairs. Adding business context can change results; this is not a production-protection guarantee.
This project has not been run independently here. Author-reported results are not independently verified results.