Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification, flagging direct injections (system-prompt overrides, role-play escapes) and indirect injections (encoded payloads, obfuscation) per OWASP LLM Top 10 (LLM01:2025). Use for input validation layers in chatbots/agents/RAG pipelines, or for retrospectively classifying injection attempts in logs or incident investigations.
Install
KitScout test notes
Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.
Similar tools
ponytail-audit190,451 ★ Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most imp
ponytail-debt190,451 ★ Harvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot
security-and-hardening117,221 ★ Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling us
deal-with-security-advisory113,505 ★ Handle confidential GitHub Security Advisory response for Paperclip. Use when coordinating advisory triage, pr
html-ppt-knowledge-arch-blueprint107,550 ★ OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups