Protect your LLMs from prompt injection and jailbreak attacks. Easy-to-use Python package with multiple detection methods, CLI tool, and FastAPI integration.
active 2025-12-30 → 2026-08-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 226 days from 2025-12-30 to 2026-08-12. Pushes: 17 total, peak 6 in a day. Pull requests: 3 total, peak 2 in a day. Issues: 10 total, peak 8 in a day. Comments: 1 total, peak 1 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| dronefreak | 27 | 15 | 2 | 1 |
| Testady21 | 2 | 2 | 0 | 0 |
| vaibhav-research | 2 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#28dronefreak2026-02-07 19:20gitHub WorkFlow Enhacement
- Issue#27dronefreak2026-02-07 19:18Ship a curated attack dataset with an evaluation CLI so users can benchmark their own threats.
- Issue#25dronefreak2026-02-07 19:13Integration examples for OpenAI/LangChain/FastAPI so developers can add PromptScreen in 10 minutes.
- Issue#26dronefreak2026-02-07 19:12Publish accuracy metrics , known limitations for SVM model that its was trained on.
- Issue#26dronefreak2026-02-07 19:12Publish accuracy metrics , known limitations for SVM model that its was trained on.
- Issue#26dronefreak2026-02-07 19:12Publish accuracy metrics , known limitations for SVM model that its was trained on.
- Issue comment#27dronefreak2026-02-07 19:11Ship a curated attack dataset with an evaluation CLI so users can benchmark their own threats.
- Issue#27dronefreak2026-02-07 19:10Ship a curated attack dataset with an evaluation CLI so users can benchmark their own threats.
- Issue#25vaibhav-research2026-02-07 18:24Integration examples for OpenAI/LangChain/FastAPI so developers can add PromptScreen in 10 minutes.
- Pull request#23vaibhav-research2026-02-05 19:57
- Issue#4dronefreak2026-01-01 14:47Add unittests and coverage reports
- Issue#5dronefreak2026-01-01 14:47Add pre-commit hooks
- Pull request#22dronefreak2026-01-01 14:38
- Pull request#22dronefreak2026-01-01 11:37
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.