Prompt Injection Detection Python Packages

arcjet

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

sunglasses

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,569 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.

arcjet-sensitive-info-rampart

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

little-canary

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

grey-panda

The calm guardian for AI, agent, and MCP code — a zero-dependency, OWASP-anchored AI security toolkit.

shadowshield

Unified open-source security shield for agentic AI systems — defense-in-depth prompt-injection protection (canary tokens, agent-trace alignment audit, tool-call guarding, PII/secret scanning).

patronus-api-client

Security scanner and runtime protection for AI coding agents. Detects prompt injection, secrets, PII, and unsafe tool activity across Codex, Claude Code, and DeepSeek Harness.

bastion-prompt-protection

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.

jamjet-guardrails

Deterministic content guardrails for LLM and agent applications. Prompt injection in the encoding, PII, secrets and your own rules, with published precision and recall and provenance on every decision.

zirah-mcp

Zirah: open-source, offline-first security scanner for MCP servers. Catches tool poisoning, prompt injection and leaked secrets before your AI agent connects. CLI + SARIF for CI.

ai-agent-shield

Defensive overlay for AI agents — an 8-layer security stack that inspects, sanitizes, audits, and blocks risky actions before they reach the host.

lockllm

Official Python SDK for LockLLM

occludra

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

aisg

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

jailguard

Pure-Rust prompt-injection detector with 1.5MB embedded MLP classifier. 98.40% accuracy, p50 14ms CPU inference, bindings for Python/JS/Go. Apache-2.0/MIT alternative to Rebuff (archived) and Lakera Guard.

sarthiai-drishti

Self-hostable content safety for LLM systems: prompt-injection detection, PII detection and redaction, and output-safety scoring. A Rust core that runs on your own hardware and returns calibrated scores, not verdicts. Ships as a Rust crate, Python and Node SDKs, an HTTP server, and a Docker image.

jamjet-guardrails-validators

Deterministic content guardrails for LLM and agent applications. Prompt injection in the encoding, PII, secrets and your own rules, with published precision and recall and provenance on every decision.

sarthiai-drishti-sdk

Self-hostable content safety for LLM systems: prompt-injection detection, PII detection and redaction, and output-safety scoring. A Rust core that runs on your own hardware and returns calibrated scores, not verdicts. Ships as a Rust crate, Python and Node SDKs, an HTTP server, and a Docker image.

jamjet-guardrails-nemo

Deterministic content guardrails for LLM and agent applications. Prompt injection in the encoding, PII, secrets and your own rules, with published precision and recall and provenance on every decision.

llama-index-postprocessor-bastion-guardrail

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.