Indirect Prompt Injection Python Packages

q-uestionable-ai

Agentic AI Security Research

agentprobe-injection

Defense evaluation harness for LLM agents — measure resistance to indirect prompt injection and compare defense effectiveness (delimiter, sandwich, screening, etc.)

renfield-mcp

Renfield — penetration testing for AI agents: finds and PROVES cross-server confused-deputy exfiltration chains in an MCP tool mesh, measures whether a real LLM falls for them, gates them at runtime, and runs as an MCP server any agent can call.

buzur

AI prompt injection defense scanner for agents. 25 phases covering HTML obfuscation, encoding attacks, semantic similarity, behavioral anomaly detection, multi-step attack chains, and more.

janus-guard

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

yara-gen

Generate YARA rules automatically from positive and negative examples. For PII detection, secret scanning, and prompt injection.

tessera-rs

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

yaramint

Generate YARA rules automatically from positive and negative examples. For PII detection, secret scanning, and prompt injection.