--- id: "/tags/safety-security-interpretability/page/3/" title: "Safety Security Interpretability · page 3" url: "https://skillissue.dev/tags/safety-security-interpretability/page/3/" --- # Safety Security Interpretability [Beginner](/levels/beginner/index.md) [Intermediate](/levels/intermediate/index.md) [Advanced](/levels/advanced/index.md) [Expert](/levels/expert/index.md) 124 resources · page 3 of 4 - ### [AI security / prompt injection](/security-and-red-teaming/safety-and-alignment-evals/ai-security-prompt-injection/index.md) by [OWASP Gen AI Security Project](https://genai.owasp.org/) OWASP Gen AI Security Project archive of Top 10 risk lists for LLM applications. Intermediate learning_resource guide Global en - ### [Apollo Research: Science](/security-and-red-teaming/safety-and-alignment-evals/apollo-research/index.md) by [Apollo Research](https://apolloresearch.ai/) Apollo Research science page listing its research and pre-deployment evaluations on AI scheming and mitigations. Intermediate–Advanced learning_resource docs UK en - ### [Beyond permission prompts (sandboxing)](/security-and-red-teaming/safety-and-alignment-evals/beyond-permission-prompts-sandboxing/index.md) by [Anthropic](https://anthropic.com/) Anthropic engineering post on Claude Code's filesystem and network sandboxing to reduce permission prompts. Intermediate learning_resource blog US en - ### [BSI Künstliche Intelligenz](/security-and-red-teaming/safety-and-alignment-evals/bsi-k-nstliche-intelligenz/index.md) by [German Federal Office for Information Security (BSI)](https://www.bsi.bund.de/) German Federal Office for Information Security (BSI) AI page with security guidance and publications on AI systems. Intermediate learning_resource guide Germany en|de - ### [Constitutional Classifiers](/security-and-red-teaming/safety-and-alignment-evals/constitutional-classifiers/index.md) by [Anthropic](https://anthropic.com/) Anthropic research post on Constitutional Classifiers, a method for defending LLMs against universal jailbreaks. Intermediate learning_resource blog US en - ### [Giskard documentation](/security-and-red-teaming/safety-and-alignment-evals/giskard-documentation/index.md) by [Giskard](https://www.giskard.ai/) Giskard documentation: open-source library and platform for testing, evaluating and red-teaming LLM agents. Intermediate learning_resource docs France en - ### [Google SAIF](/security-and-red-teaming/safety-and-alignment-evals/google-saif/index.md) by [Google](https://safety.google/) Google Secure AI Framework (SAIF): six core elements for AI model security, risk management and privacy. Intermediate learning_resource guide US 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) by [Kai Greshake et al. (Saarland University)](https://www.uni-saarland.de/) arXiv paper (2023) by Greshake et al. introducing indirect prompt injection against LLM-integrated applications. Intermediate learning_resource paper Germany en - ### [Hermes Agent docs: Security](/security-and-red-teaming/safety-and-alignment-evals/hermes-agent-security/index.md) by [Nous Research](https://nousresearch.com/) Hermes Agent security documentation: command approval, user authorisation, container isolation and deployment practices. Intermediate learning_resource docs US en - ### [HiddenLayer research](/security-and-red-teaming/safety-and-alignment-evals/hiddenlayer-research/index.md) by [HiddenLayer](https://hiddenlayer.com/) HiddenLayer research page publishing findings on AI vulnerabilities, adversarial attacks and model security threats. Intermediate learning_resource blog US 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) by [Anthropic](https://anthropic.com/) Anthropic engineering post on how Claude Code auto mode decides when to skip permission prompts safely. Intermediate learning_resource blog US en - ### [Interpretable Machine Learning](/security-and-red-teaming/safety-and-alignment-evals/interpretable-machine-learning/index.md) by [Christoph Molnar](https://christophm.github.io/) Christoph Molnar's Interpretable Machine Learning book: free online guide to explainability methods and their limits. Intermediate learning_resource guide Germany 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) by [Courts and Tribunals Judiciary](https://judiciary.uk/) UK Judiciary guidance (PDF, October 2025) for judicial office holders on AI use cases, risks and verification duties. Intermediate learning_resource guide United Kingdom en - ### [Lakera blog](/security-and-red-teaming/safety-and-alignment-evals/lakera-blog/index.md) by [Lakera](https://www.lakera.ai/) Lakera blog on AI security, prompt injection and LLM attacks, with research posts and product news. Intermediate learning_resource blog US en - ### [Many-shot jailbreaking](/security-and-red-teaming/safety-and-alignment-evals/many-shot-jailbreaking/index.md) by [Anthropic](https://anthropic.com/) Anthropic research on many-shot jailbreaking, a long-context attack using many faux dialogue examples. Intermediate learning_resource paper US 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) by [Matt Palmer](https://mattpalmer.io/) Matt Palmer's statement on CVE-2025-48757: missing row-level security in Lovable-generated apps exposed user data. Intermediate learning_resource guide US en - ### [MCP blog: Tool annotations](/security-and-red-teaming/safety-and-alignment-evals/mcp-blog-tool-annotations-2026-03-16/index.md) by [Model Context Protocol](https://modelcontextprotocol.io) MCP blog post on tool annotations such as read-only and destructive hints, and how far clients should trust them. Intermediate learning_resource blog Global en - ### [MCP docs: Local server security](/security-and-red-teaming/safety-and-alignment-evals/mcp-local-server-security/index.md) by [Model Context Protocol](https://modelcontextprotocol.io) MCP documentation on hardening local stdio MCP servers. Intermediate learning_resource docs Global en - ### [MITRE ATLAS](/security-and-red-teaming/safety-and-alignment-evals/mitre-atlas/index.md) by [MITRE](https://www.mitre.org/) MITRE ATLAS: knowledge base and ATT&CK-style matrix of adversary tactics and techniques against AI systems. Intermediate learning_resource docs US 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) by [UK National Cyber Security Centre (NCSC)](https://www.ncsc.gov.uk/) UK NCSC and partner guidelines for secure AI system development across design, development, deployment and operation. Intermediate learning_resource guide UK 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) by [Neel Nanda](https://www.neelnanda.io/) Neel Nanda's AI Alignment Forum guide on how to become a mechanistic interpretability researcher, which replaced his earlier getting-started page. Intermediate learning_resource guide UK 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) by [NIST](https://nist.gov/) NIST AI 100-2 report: taxonomy and terminology of adversarial machine learning attacks and mitigations. Intermediate–Advanced learning_resource docs US 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) by [OWASP Gen AI Security Project](https://genai.owasp.org/) OWASP Top 10 for Agentic Applications 2026: list of security risks specific to AI agents. Intermediate learning_resource guide Global en - ### [Patronus AI](/security-and-red-teaming/safety-and-alignment-evals/patronus-ai/index.md) by [Patronus AI](https://www.patronus.ai/) Patronus AI blog with posts on LLM evaluation, benchmarks and AI reliability research. Intermediate learning_resource blog US 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) by [Google Project Zero](https://projectzero.google/) Google Project Zero post on Big Sleep, an LLM agent that found an exploitable SQLite vulnerability in real code. Intermediate learning_resource guide US 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) by [promptfoo](https://promptfoo.dev) Promptfoo documentation mapping its red-teaming plugins to the OWASP LLM Top 10 risks. Intermediate learning_resource guide US 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) by [Deep Ganguli et al. (Anthropic)](https://www.anthropic.com/) arXiv paper (2022) by Anthropic on red teaming language models: methods, scaling behaviour and a released attack dataset. Intermediate learning_resource paper US en - ### [Redwood Research](/security-and-red-teaming/safety-and-alignment-evals/redwood-research/index.md) by [Redwood Research](https://redwoodresearch.org/) Redwood Research page listing its research on AI control and keeping AI systems aligned with developer intent. Intermediate–Advanced learning_resource docs US 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) by [Retraction Watch](https://retractionwatch.com/) Retraction Watch running list of published papers and peer reviews containing evidence of ChatGPT-written text. Intermediate learning_resource guide Global 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) by [Khan Academy](https://www.khanacademy.org/) Sal Khan's reflection on the first chapter of the Khanmigo AI tutor and what it changed for student learning. Intermediate learning_resource guide US en - ### [Simon Willison on prompt-injection](/security-and-red-teaming/safety-and-alignment-evals/simon-willison-prompt-injection-tag/index.md) by [Simon Willison](https://simonwillison.net/) Simon Willison's prompt-injection tag: running record of prompt-injection attacks and incidents since 2022. Intermediate learning_resource guide UK/US en - ### [The lethal trifecta for AI agents (Simon Willison)](/security-and-red-teaming/safety-and-alignment-evals/simon-willison-the-lethal-trifecta/index.md) by [Simon Willison](https://simonwillison.net/) Simon Willison's post on the lethal trifecta: private data, untrusted content and exfiltration make AI agents exploitable. Intermediate learning_resource guide UK/US en [Previous page](/tags/safety-security-interpretability/page/2/index.md) [Next page](/tags/safety-security-interpretability/page/4/index.md) [Plain-text Markdown copy](/tags/safety-security-interpretability/page/3/index.md)