llm-fw PIsberg · COMPLETED
A local prompt injection firewall that intercepts traffic between your tools and every major LLM API before it leaves your machine. Malicious prompts are blocked and logged; clean ones are forwarded transparently.
github.com/PIsberg/llm-fw · ★ 5 · Forks 1 · Size 8.1 MB
SUMMARY
Technologies 15
Scored 15
Observed 15
Practices 6
Evidence 16
Skips 0
COVERAGE
Analyzed 372 files · 645 commits · 0 API calls
TECHNOLOGIES & DEPTH
TypeScript LANGUAGE Depth 70
208 files · PRODUCTION
Dockerfile LANGUAGE Depth 70
1 files · PRODUCTION
JavaScript LANGUAGE Depth 70
7 files · PRODUCTION
JSON LANGUAGE Depth 70
10 files · PRODUCTION
Markdown LANGUAGE Depth 70
68 files · PRODUCTION
YAML LANGUAGE Depth 70
19 files · PRODUCTION
Python LANGUAGE Depth 70
4 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
npm BUILD_TOOL Depth 80
1 files · CONFIGURATION
ESLint QUALITY Depth 69
3 files · CONFIGURATION
MongoDB DATABASE Depth 88
3 files · CONFIGURATION, PRODUCTION, TEST
Playwright TESTING Depth 78
8 files · PRODUCTION, TEST
Vitest TESTING Depth 53
104 files · TEST
debug LIBRARY Depth 58
1 files · PRODUCTION
pytest TESTING Depth 32
1 files · TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · observedlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-05-30
Last commit 2026-09-24
Active months 5
Commits 645