Lightweight prompt injection detector + LLM output scanner. 75 input patterns + output scanning for secrets, PII, system prompt leakage, hallucinated URLs, and code safety. Zero ML dependencies.
[email protected] low health (48/100) — consider alternatives
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/pypi/ai-injection-guardLast updated · 2026-03-14T15:13:28.021812Z