w4-advisory / plexiglass
A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
Why this job: topics: security, cybersecurity
What it does
Plexiglass evaluates explicit security assertions against JSON HTTP application endpoints and Python callables. The first milestone supports controlled prompt-injection tests, synthetic data-leakage checks, benign controls, complete evidence, and baseline regression gates.
Get started
python -m pip install -e .
python examples/fixture_server.py - Maintenance
- Active
- Last commit 5 days ago
- Stars
- 156
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 8 merged
- 4 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| elder-plinius / L1B3RT4S | 23,217 | 12 days ago | AGPL-3.0 | No downloads |
| openhackai / OpenHack | 441 | 23 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- Makefile <1%
- Shell <1%
Topics
- adversarial-attacks
- deep-learning
- cybersecurity
- machine-learning
- deep-neural-networks
- security
- adversarial-machine-learning
Project record
- JobAI security
- StatusListed
- Commits149
- Forks18
- Watching5
- Stars in 28 days0
- CreatedNov 12, 2020
- First seen by usNov 7, 2026
- CheckedNov 8, 2026