AI Security
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.
Nov 22, 20257 min read
Resources
Supply Chain Security, in plain English.
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
Filter
Articles
RSS feedAI Security
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.
Nov 20, 20255 min read
AI Security
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.
Nov 20, 20257 min read
AI Security
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.
Nov 19, 20257 min read
AI Security
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.
Nov 18, 20255 min read
AI Security
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.
Nov 18, 20257 min read
AI Security
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.
Nov 18, 20257 min read
AI Security
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.
Nov 18, 20257 min read
AI Security
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.
Nov 18, 20257 min read
Stay informed
Weekly insights on software supply chain security, delivered to your inbox.
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.