# Security And Red Teaming

> Free resources, with credit to the original creators.

## Resources
- [NIST AI Risk Management Framework](/security-and-red-teaming/threat-frameworks-and-standards/nist-nist-ai-risk-management-framework/index.md): A government reference for organizing AI risk-management work. (intermediate; West; closed resource; by NIST)
- [OWASP Top 10 for LLM Applications 2025](/security-and-red-teaming/threat-frameworks-and-standards/owasp-gen-ai-security-project-owasp-top-10-for-llm-applications-2025/index.md): Use a shared vocabulary for discussing risks in LLM applications. (intermediate; other; closed resource; by OWASP Gen AI Security Project)
- [Simon Willison on prompt injection](/security-and-red-teaming/prompt-injection/simon-willison-simon-willison-on-prompt-injection/index.md): Follow an ongoing public record of prompt-injection research. (intermediate; West; closed resource; by Simon Willison)
- [The lethal trifecta for AI agents](/security-and-red-teaming/agent-and-tool-security/willison-lethal-trifecta/index.md): A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs. (intermediate; West; closed resource; by Simon Willison)
- [Agentic misalignment](/security-and-red-teaming/safety-and-alignment-evals/anthropic-agentic-misalignment/index.md): A controlled study of risky behavior under conflicting agent incentives. (advanced; West; closed resource; by Anthropic)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](/security-and-red-teaming/prompt-injection/greshake-indirect-prompt-injection/index.md): Foundational public research on indirect prompt injection. Linked only; no payloads reproduced. (advanced; West; closed resource; by Kai Greshake et al.)
- [Embrace The Red](/security-and-red-teaming/prompt-injection/johann-rehberger-embrace-the-red/index.md): Public case reports about security failures in deployed AI products. (advanced; West; closed resource; by Johann Rehberger)
- [MITRE ATLAS](/security-and-red-teaming/threat-frameworks-and-standards/mitre-mitre-atlas/index.md): Connect AI threats with documented techniques, mitigations and cases. (advanced; West; closed resource; by MITRE)
- [garak - LLM vulnerability scanner](/security-and-red-teaming/security-tooling/nvidia-garak-llm-vulnerability-scanner/index.md): A public scanner project for understanding classes of model failures. (advanced; West; open resource; by NVIDIA)
- [promptfoo](/security-and-red-teaming/security-tooling/promptfoo-promptfoo/index.md): Inspect a project combining application evaluation and security testing. (advanced; West; open resource; by promptfoo)
- [Design Patterns for Securing LLM Agents against Prompt Injections](/security-and-red-teaming/agent-and-tool-security/willison-prompt-injection-design-patterns/index.md): Summary of a paper's defensive agent architectures. (advanced; West; closed resource; by Simon Willison)