liu00222 / Open-Prompt-Injection
This repository provides a benchmark for prompt injection attacks and defenses in LLMs
Why this job: says: prompt injection; topics: llm-security, prompt-injection
What it does
This repository is an open-source toolkit for prompt injection attacks and defenses. It enables implementation, evaluation, and extension of attacks, defenses, and LLM-integrated applications and agents. For a deeper dive into prompt injection, see these slides, an extended version of a presentation given at the Safer with Google Summit 2025.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 43 days ago
- Stars
- 512
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 94% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 90% closed
- 2 still open
- Pull requests
- 8 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| uber / ADR | 2,128 | 24 days ago | Apache-2.0 | No downloads |
| secureagentics / Adrian | 589 | 19 days ago | Apache-2.0 | No downloads |
| PrismorSec / prismor | 480 | 2 days ago | Apache-2.0 | Mac, Windows, Linux |
More: languages, topics and project record
Languages
- Python 94%
- Jupyter Notebook 6%
Topics
- llm-security
- llms
- prompt-injection
- prompt-injection-tool
- llm
- security-and-privacy
Project record
- JobAI security
- StatusListed
- Commits69
- Forks83
- Watching3
- Stars in 28 days+8
- CreatedOct 19, 2023
- First seen by usNov 7, 2026
- CheckedNov 8, 2026