AI Security
In-depth guides and analysis on ai security from the Safeguard engineering team.
779 articles
vLLM CVE-2025-66448: Auto-Map RCE via Model Configs
A critical RCE in vLLM allows malicious model configs to bypass trust_remote_code=False. We analyze the bug, the patch, and what every vLLM operator should do.
Anthropic's Responsible Scaling Policy v3: What Changed
RSP v3.0 takes effect February 24, 2026. It splits the AI R&D threshold, adds a CBRN-development tier, and formalizes Risk Reports.
Gemini 3 Pro and the Frontier Safety Framework Report
Google released Gemini 3 Pro on November 18, 2025 with the most thorough Frontier Safety Framework evaluation yet. We unpack what was disclosed and how it changes downstream defender posture.
ShadowMQ: 30+ RCE Flaws Across AI Inference Engines
Oligo Security disclosed ShadowMQ in November 2025: ZeroMQ-and-pickle deserialization patterns copy-pasted across vLLM, Meta Llama, TensorRT-LLM, and others. We dissect the pattern.
Training Data Provenance for Enterprise Fine-Tuning
Fine-tuning corpora are supply chain artifacts. We cover the provenance signals, attestations, and drift controls enterprises need before pushing weights to prod.
Rogue AI Agents: When Autonomous Systems Act Outside Inte...
Autonomous AI agents are gaining real access to production systems — and real incidents, from deleted databases to fabricated refunds, show what happens when they act outside intended boundaries.
Human-Agent Trust Exploitation in AI Systems
Attackers are exploiting the trust between humans and AI agents — hidden prompt injections, hallucinated packages, and over-trusted autonomy are now supply chain risks.
Cascading Failures in Multi-Agent AI Architectures
One compromised agent can poison an entire pipeline in seconds. Heres how cascading failures spread through multi-agent AI systems, and how to contain them.
Insecure Inter-Agent Communication in Multi-Agent Systems
Multi-agent AI pipelines pass untrusted content between agents with no authentication or integrity checks. Here's how insecure inter-agent communication opens the door to injection attacks.
Uncontrolled Recursion in AI Agent Loops
AI agents can call themselves into runaway loops, burning thousands of dollars and crashing services. Here's why it happens and how to stop it.
Memory and Context Poisoning Attacks Against AI Agents
How attackers poisoned ChatGPT's memory and RAG pipelines to hijack AI agents long-term, and the controls Safeguard uses to catch it before it spreads.
Agentic Unexpected Code Execution Vulnerabilities
How AI agents with code-execution tools get hijacked by prompt injection—from the Vanna.ai RCE (CVE-2024-5565) to LangChain and MCP—and what to do about it.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.