AI Security
Prompt Injection in RAG: Indirect Attacks
A senior engineer's breakdown of indirect prompt injection in RAG pipelines, how real attacks land through retrieved content, and what actually reduces exposure.
Apr 5, 20267 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
Scoped Credentials Per MCP Server: A Pattern
Long-lived shared tokens are the wrong unit of trust for MCP servers. Here is the per-server scoped-credential pattern and how to roll it out.
Apr 4, 20267 min read
AI Security
MCP Vulnerability Disclosure Trends In 2026
MCP servers went from a niche protocol to standard agent infrastructure in under two years. The vulnerability disclosure landscape is catching up — fast, messily, and with patterns worth tracking.
Apr 4, 20267 min read
AI Security
Real-World Deployment: Griffin AI vs Mythos
Demos live on a single repo and a curated dataset. Real deployments hit fifty repos, three CI providers, two cloud accounts, and an air-gapped environment. The gap is where vendors get sorted.
Apr 4, 20265 min read
AI Security
Agentic Procurement: Letting AI Agents Buy Software Safely
Agents can now evaluate, trial, and pay for software without a human in the loop. The controls that make that safe: spend caps, allowlists, verifiable merchants, and audit trails.
Apr 4, 20266 min read
AI Security
Breaking-Change-Aware Remediation In 2026
Most fix PRs fail because they ignore breaking changes in the patched version. Here is how breaking-change-aware remediation closes vulns without regressions.
Apr 3, 20267 min read
AI Security
MCP Server Telemetry Data Governance
MCP server telemetry captures sensitive prompts, arguments, and outputs. A governance framework for retention, redaction, and tenant-scoped access is essential.
Apr 2, 20268 min read
AI Security
How DevOps Teams Actually Use AI Today
How can a DevOps team take advantage of artificial intelligence without adding risk? Mostly by pointing it at toil — log triage, test generation, and incident summarization — not by handing it the keys to production.
Apr 2, 20265 min read
AI Security
AI Agent Tool Calling Security: Risks and Mitigations
AI agents that call tools -- APIs, databases, file systems, code interpreters -- convert non-deterministic LLM output into real-world actions. Securing this boundary is the defining challenge of agentic AI.
Apr 1, 20267 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.