Safeguard
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.

All (1720)Vulnerability Analysis (12009)Security Guides (5118)Application Security (3307)Developer Tools (2961)Compliance (2830)AI Security (1720)Supply Chain (1423)Supply Chain Security (1025)Industry Analysis (1005)Research (585)Security (532)DevSecOps (511)Product (509)Tool Comparison (454)Open Source Security (417)Incident Analysis (399)AppSec (309)Cloud Security (300)Container Security (287)Software Supply Chain (282)Best Practices (264)Open Source (252)Buyer's Guides (217)Software Supply Chain Security (182)Vulnerability Management (150)Regulatory Compliance (144)Ranking (116)Concepts (116)Containers (100)Supply Chain Attacks (93)SBOM (77)Vulnerabilities (74)Threat Intelligence (66)Infrastructure Security (65)FAQ (50)Tools (50)SBOM & Compliance (41)Comparisons (36)Engineering (29)Licensing (26)Ransomware (24)Tutorials (24)SecOps (22)Guides (22)Kubernetes Security (22)Vulnerability Guides (20)Regulation (20)Industry Guides (19)Case Studies (18)Compliance & Regulations (18)Emerging Technology (17)Solutions (17)Risk Management (16)Vulnerability Response (16)Tool Reviews (16)Agent Security (16)Threat Research (16)Compliance & Frameworks (15)Incident Response (15)Identity Security (15)Cryptography (15)Security Concepts (15)Industry Events (14)Security Strategy (13)Frameworks (12)Web Security (11)Data Breach (11)Dependency Security (11)Career (10)Security News (10)Buyer Guides (10)Culture (9)Enterprise (9)Company (9)Architecture (8)Standards (8)Vulnerability Research (8)Strategy (8)Secure Development (7)Industry Insights (7)Industry Trends (7)Zero-Day Exploits (7)Network Security (7)How-To Guide (7)Dependency Management (7)Vendor Comparison (6)Security Operations (6)Organizational Security (6)Developer Security (6)Industry (6)Dev Practices (6)Code Security (5)Breach Analysis (5)Cryptocurrency Security (4)Product Launch (4)Mobile Security (4)Policy (4)Offensive Security (4)Tool Comparisons (4)Healthcare Security (3)Governance (3)Social Engineering (3)Hardware Security (3)Build Security (3)Policy & Compliance (3)API Security (3)Regional Security (3)Startup Security (3)Analysis (3)SBOM Standards (2)DeFi Security (2)Industry News (2)Security Architecture (2)Security Management (2)SBOM and Compliance (2)Zero-Day Analysis (2)Release (2)Security Culture (2)Threat Actors (2)Tools & Platforms (1)Tools & Techniques (1)Events (1)Architecture Security (1)Career Development (1)Browser Security (1)SBOM & Standards (1)Incident Postmortem (1)Kubernetes (1)Nation-State Threats (1)Language Security (1)Perspectives (1)Privacy & Security (1)Threat Analysis (1)Runtime Security (1)Emerging Threats (1)Threat Modeling (1)Healthcare (1)Data Security (1)Safeguard runs on VR and mixed reality headsets. Where a spatial view of your software estate helps, and where a plain screen is still better. (1)PKI Security (1)Privacy (1)Product Update (1)Technical (1)Lifecycle Management (1)Credential Attacks (1)Business Continuity (1)

Articles

RSS feed
AI Security

VS Code 1.136.2: Copilot Agent Data Leak and Network Policy Bypasses

September's VS Code fixes include CVE-2026-81380, where prompt injection could make Copilot agent mode send environment variables out, and four agent network policy bypasses.

Oct 18, 20265 min read
AI Security

Fake Web3 Accelerator Ships npm 'AI Copilot' That Reroutes Agent Traffic

Elastic traced @apexacc/cli and @apexacc/audit to a fake Web3 accelerator. The CLI dropped stealers and sent the coding agent's model traffic and MCP calls to attacker servers.

Oct 18, 20265 min read
AI Security

LiteLLM CVE-2026-59822: Fake Bearer Tokens Reached MCP Tools

A fallback in LiteLLM's MCP auth let any made-up Bearer token open an authenticated MCP session. Fixed in 1.84.0; CISA added it to KEV on 2 September 2026.

Oct 18, 20265 min read
AI Security

Who Can Your AI Agent Call? Layered Access Control for MCP Tools

Every Safeguard MCP tool call is now checked at tenant, organization, role and agent level. New tenants start with reads on and writes off.

Oct 17, 20263 min read
AI Security

Authorization Belongs in the Tool, Not in the Prompt

Your support chatbot can now issue refunds and look up orders, because someone connected it to real tools. Every one of those actions sits behind a customer-facing text box, protected however carefully the prompt was worded.

Sep 18, 20266 min read
AI Security

A Poisoned Memory Outlives the Conversation That Created It

Prompt injection in a single turn affects one response, then the next request starts clean. A persistent memory feature breaks that boundary by design, so a single successful injection becomes durable, recalled and trusted in every future session.

Sep 18, 20265 min read
AI Security

Writing an MCP Server That Holds No Credentials

Give a model a tool that writes and you have added a route into whatever sits behind it. The design that keeps it a new shape rather than a new privilege, and the four things that were not obvious.

Sep 17, 20267 min read
AI Security

The AI Code Percentage On Your Dashboard Is a Floor, Not a Measurement

Commit-level attribution answers 'lines added by commits an assistant co-authored'. That is a different sentence from 'lines an AI wrote', and the gap between them is where governance metrics go wrong.

Aug 13, 20265 min read
AI Security

Your Git History Already Knows Which AI Wrote Your Code

Coding assistants sign their own work in the commit trailer block. That makes 'how much of this was AI-written' a parsing problem, not a heuristic one — as long as your tooling reads the commit body, which most of it does not.

Aug 13, 20265 min read

Stay informed

Weekly insights on software supply chain security, delivered to your inbox.

We email you a link to confirm, and only then add you to the list. Unsubscribe in one click. Privacy

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.