Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.

System-level security for LLM agents: fine-grained policy enforcement on tool calls to defend against indirect prompt injection

Transform any content into 9 platform-native formats or convert between content types — with optional brand voice matching. Supports Twitter/X, LinkedIn, newsletter, Instagram, YouTube Shorts, TikTok, Threads, Bluesky, and podcast. Secure-by-default: includes prompt injection defenses for safe URL and web content processing.

Reproducible security benchmarking for the Deconvolute SDK and AI system integrity against adversarial attacks.

Signed provenance labels and taint-tracking policy for LLM agent security. The core library behind AgentMesh.

Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration shapes (secret read plus network, env dump to network, remote script to shell, reverse shells). A sanitizing MCP server wraps untrusted URLs and files in sentinels, strips invisible unicode, flags jailbreaks.

Automatically generate YARA rules from adversarial and benign text samples. Built for detecting indirect prompt injection attacks on RAG pipelines.

AgentForensics is an open-source security framework that monitors complete LLM agent sessions in real time, detecting prompt injection attacks across tool outputs, web pages, documents, and API responses. It uses heuristic rules, a DistilBERT ML classifier, instruction boundary detection, semantic drift, and sliding-window multi-turn detection.

Research artifact, paper, and frozen evaluation outputs for selective revocation and replay after persistent indirect prompt injection in memory-augmented LLM agents.

Agentic AI Security Research

Buzur is an open-source 25-phase scanner that protects AI agents and LLM applications from indirect prompt injection attacks (OWASP LLM Top 10 #1).

Buzur is an open-source 25-phase scanner that protects AI agents and LLM applications from indirect prompt injection attacks (OWASP LLM Top 10 #1).