--- id: "/security-and-red-teaming/safety-and-alignment-evals/page/3/" title: "Safety And Alignment Evals: 126 curated resources · page 3" creator: null creator_url: null creator_x: null url: "https://skillissue.dev/security-and-red-teaming/safety-and-alignment-evals/page/3/" level: null level_max: null category: null subcategory: null region: null license: null license_scope: null access: null models: null source_date: null date_added: null resource_kind: null verification_basis: null access_evidence: null domain_top: null domain_sub: null last_verified: null --- # Safety And Alignment Evals: 126 curated resources Curated material on safety and alignment evals within security and red teaming. [Beginner](/security-and-red-teaming/beginner/index.md) [Intermediate](/security-and-red-teaming/intermediate/index.md) [Advanced](/security-and-red-teaming/advanced/index.md) [Expert](/security-and-red-teaming/expert/index.md) 126 resources · page 3 of 4 - ### [AI security / prompt injection](/security-and-red-teaming/safety-and-alignment-evals/ai-security-prompt-injection/index.md) Creator not supplied; see original source. OWASP Gen AI Security Project archive of Top 10 risk lists for LLM applications. Intermediate · unknown · unknown resource · en - ### [Apollo Research: Science](/security-and-red-teaming/safety-and-alignment-evals/apollo-research/index.md) Creator not supplied; see original source. Apollo Research science page listing its research and pre-deployment evaluations on AI scheming and mitigations. Intermediate–Advanced · unknown · unknown resource · en - ### [Beyond permission prompts (sandboxing)](/security-and-red-teaming/safety-and-alignment-evals/beyond-permission-prompts-sandboxing/index.md) Creator not supplied; see original source. Anthropic engineering post on Claude Code's filesystem and network sandboxing to reduce permission prompts. Intermediate · unknown · unknown resource · en - ### [BSI Künstliche Intelligenz](/security-and-red-teaming/safety-and-alignment-evals/bsi-k-nstliche-intelligenz/index.md) Creator not supplied; see original source. German Federal Office for Information Security (BSI) AI page with security guidance and publications on AI systems. Intermediate · unknown · unknown resource · en|de - ### [Constitutional Classifiers](/security-and-red-teaming/safety-and-alignment-evals/constitutional-classifiers/index.md) Creator not supplied; see original source. Anthropic research post on Constitutional Classifiers, a method for defending LLMs against universal jailbreaks. Intermediate · unknown · unknown resource · en - ### [Giskard documentation](/security-and-red-teaming/safety-and-alignment-evals/giskard-documentation/index.md) Creator not supplied; see original source. Giskard documentation: open-source library and platform for testing, evaluating and red-teaming LLM agents. Intermediate · unknown · unknown resource · en - ### [Google SAIF](/security-and-red-teaming/safety-and-alignment-evals/google-saif/index.md) Creator not supplied; see original source. Google Secure AI Framework (SAIF): six core elements for AI model security, risk management and privacy. Intermediate · unknown · unknown resource · en - ### [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](/security-and-red-teaming/safety-and-alignment-evals/greshake-et-al-indirect-prompt-injection/index.md) Creator not supplied; see original source. arXiv paper (2023) by Greshake et al. introducing indirect prompt injection against LLM-integrated applications. Intermediate · unknown · unknown resource · en - ### [Hermes Agent docs: Security](/security-and-red-teaming/safety-and-alignment-evals/hermes-agent-security/index.md) Creator not supplied; see original source. Hermes Agent security documentation: command approval, user authorisation, container isolation and deployment practices. Intermediate · unknown · unknown resource · en - ### [HiddenLayer research](/security-and-red-teaming/safety-and-alignment-evals/hiddenlayer-research/index.md) Creator not supplied; see original source. HiddenLayer research page publishing findings on AI vulnerabilities, adversarial attacks and model security threats. Intermediate · unknown · unknown resource · en - ### [How we built Claude Code auto mode](/security-and-red-teaming/safety-and-alignment-evals/how-we-built-claude-code-auto-mode/index.md) Creator not supplied; see original source. Anthropic engineering post on how Claude Code auto mode decides when to skip permission prompts safely. Intermediate · unknown · unknown resource · en - ### [Interpretable Machine Learning](/security-and-red-teaming/safety-and-alignment-evals/interpretable-machine-learning/index.md) Creator not supplied; see original source. Christoph Molnar's Interpretable Machine Learning book: free online guide to explainability methods and their limits. Intermediate · unknown · unknown resource · en - ### [Artificial Intelligence (AI): Guidance for Judicial Office Holders](/security-and-red-teaming/safety-and-alignment-evals/judicial-office-holders-ai-guidance-october-2025/index.md) Creator not supplied; see original source. UK Judiciary guidance (PDF, October 2025) for judicial office holders on AI use cases, risks and verification duties. Intermediate · unknown · unknown resource · en - ### [Lakera blog](/security-and-red-teaming/safety-and-alignment-evals/lakera-blog/index.md) Creator not supplied; see original source. Lakera blog on AI security, prompt injection and LLM attacks, with research posts and product news. Intermediate · unknown · unknown resource · und - ### [Many-shot jailbreaking](/security-and-red-teaming/safety-and-alignment-evals/many-shot-jailbreaking/index.md) Creator not supplied; see original source. Anthropic research on many-shot jailbreaking, a long-context attack using many faux dialogue examples. Intermediate · unknown · unknown resource · en - ### [Statement on CVE-2025-48757 (Matt Palmer)](/security-and-red-teaming/safety-and-alignment-evals/matt-palmer-statement-on-cve-2025-48757-2025-05-29/index.md) Creator not supplied; see original source. Matt Palmer's statement on CVE-2025-48757: missing row-level security in Lovable-generated apps exposed user data. Intermediate · unknown · unknown resource · en - ### [MCP blog: Tool annotations](/security-and-red-teaming/safety-and-alignment-evals/mcp-blog-tool-annotations-2026-03-16/index.md) Creator not supplied; see original source. MCP blog post on tool annotations such as read-only and destructive hints, and how far clients should trust them. Intermediate · unknown · unknown resource · en - ### [MCP docs: Local server security](/security-and-red-teaming/safety-and-alignment-evals/mcp-local-server-security/index.md) Creator not supplied; see original source. MCP documentation on hardening local stdio MCP servers. Intermediate · unknown · unknown resource · en - ### [MITRE ATLAS](/security-and-red-teaming/safety-and-alignment-evals/mitre-atlas/index.md) Creator not supplied; see original source. MITRE ATLAS: knowledge base and ATT&CK-style matrix of adversary tactics and techniques against AI systems. Intermediate · unknown · unknown resource · en - ### [NCSC/CISA Guidelines for secure AI system development](/security-and-red-teaming/safety-and-alignment-evals/ncsc-cisa-guidelines-for-secure-ai-system-development/index.md) Creator not supplied; see original source. UK NCSC and partner guidelines for secure AI system development across design, development, deployment and operation. Intermediate · unknown · unknown resource · en - ### [How To Become A Mechanistic Interpretability Researcher](/security-and-red-teaming/safety-and-alignment-evals/neel-nanda-getting-started-in-mech-interp/index.md) Creator not supplied; see original source. Neel Nanda's AI Alignment Forum guide on how to become a mechanistic interpretability researcher, which replaced his earlier getting-started page. Intermediate · unknown · unknown resource · en - ### [NIST AI 100-2 Adversarial ML taxonomy](/security-and-red-teaming/safety-and-alignment-evals/nist-ai-100-2-adversarial-ml-taxonomy/index.md) Creator not supplied; see original source. NIST AI 100-2 report: taxonomy and terminology of adversarial machine learning attacks and mitigations. Intermediate–Advanced · unknown · unknown resource · en - ### [OWASP Top 10 for Agentic Applications 2026](/security-and-red-teaming/safety-and-alignment-evals/owasp-top-10-for-agentic-applications-2026/index.md) Creator not supplied; see original source. OWASP Top 10 for Agentic Applications 2026: list of security risks specific to AI agents. Intermediate · unknown · unknown resource · en - ### [Patronus AI](/security-and-red-teaming/safety-and-alignment-evals/patronus-ai/index.md) Creator not supplied; see original source. Patronus AI blog with posts on LLM evaluation, benchmarks and AI reliability research. Intermediate · unknown · unknown resource · en - ### [From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code](/security-and-red-teaming/safety-and-alignment-evals/project-zero-from-naptime-to-big-sleep/index.md) Creator not supplied; see original source. Google Project Zero post on Big Sleep, an LLM agent that found an exploitable SQLite vulnerability in real code. Intermediate · unknown · unknown resource · en - ### [promptfoo docs: OWASP LLM Top 10 red teaming](/security-and-red-teaming/safety-and-alignment-evals/promptfoo-owasp-llm-top-10-red-teaming/index.md) Creator not supplied; see original source. Promptfoo documentation mapping its red-teaming plugins to the OWASP LLM Top 10 risks. Intermediate · unknown · unknown resource · en - ### [Red Teaming LMs to Reduce Harms (Ganguli et al.)](/security-and-red-teaming/safety-and-alignment-evals/red-teaming-lms-to-reduce-harms-ganguli-et-al/index.md) Creator not supplied; see original source. arXiv paper (2022) by Anthropic on red teaming language models: methods, scaling behaviour and a released attack dataset. Intermediate · unknown · unknown resource · en - ### [Redwood Research](/security-and-red-teaming/safety-and-alignment-evals/redwood-research/index.md) Creator not supplied; see original source. Redwood Research page listing its research on AI control and keeping AI systems aligned with developer intent. Intermediate–Advanced · unknown · unknown resource · en - ### [Retraction Watch: papers with evidence of ChatGPT writing](/security-and-red-teaming/safety-and-alignment-evals/retraction-watch-papers-with-evidence-of-chatgpt-writing/index.md) Creator not supplied; see original source. Retraction Watch running list of published papers and peer reviews containing evidence of ChatGPT-written text. Intermediate · unknown · unknown resource · en - ### [Sal Khan: Khanmigo's First Chapter Changed How I Think About AI (Khan Academy)](/security-and-red-teaming/safety-and-alignment-evals/sal-khan-khanmigo-s-first-chapter-khan-academy-blog/index.md) Creator not supplied; see original source. Sal Khan's reflection on the first chapter of the Khanmigo AI tutor and what it changed for student learning. Intermediate · unknown · unknown resource · en - ### [Simon Willison on prompt-injection](/security-and-red-teaming/safety-and-alignment-evals/simon-willison-prompt-injection-tag/index.md) Creator not supplied; see original source. Simon Willison's prompt-injection tag: running record of prompt-injection attacks and incidents since 2022. Intermediate · unknown · unknown resource · en - ### [The lethal trifecta for AI agents (Simon Willison)](/security-and-red-teaming/safety-and-alignment-evals/simon-willison-the-lethal-trifecta/index.md) Creator not supplied; see original source. Simon Willison's post on the lethal trifecta: private data, untrusted content and exfiltration make AI agents exploitable. Intermediate · unknown · unknown resource · en [Previous page](/security-and-red-teaming/safety-and-alignment-evals/page/2/index.md) [Next page](/security-and-red-teaming/safety-and-alignment-evals/page/4/index.md) [Plain-text Markdown copy](/security-and-red-teaming/safety-and-alignment-evals/page/3/index.md)