prompt-injection
Safeguard articles tagged "prompt-injection" — guides, analysis, and best practices for software supply chain and application security.
135 articles
OWASP LLM Top 10 2025: System Prompt Leakage and Vector Weaknesses
The OWASP Top 10 for LLM Applications 2025 added System Prompt Leakage and Vector/Embedding Weaknesses, and elevated Sensitive Information Disclosure to #2. Here is the defender view.
MCP Security
MCP is standardizing how AI agents call tools, and attackers are already exploiting tool poisoning, rug pulls, and shadowing. Here's what MCP security actually requires.
Protecting GenAI: OWASP Top 10 for LLMs
OWASP's Top 10 for LLM Applications reframes AI risk around prompt injection, data poisoning, and supply chain gaps that container-only tools like Aqua can't reach.
Why LLMs Are Structurally Insecure (and What That Means for Your Pipeline)
Language models are not insecure because of a bug you can patch. They are insecure by construction — non-deterministic, context-poisonable, and unreproducible. Here is how to reason about them without pretending otherwise.
OWASP Top 10 for LLM Applications, Explained
A practitioner's walkthrough of the OWASP Top 10 for LLM Applications: what each risk looks like in a real system, which ones bite first, and the mitigations that hold up.
AI Cybersecurity Threats: The 2026 Landscape
AI has made the median attacker faster and the median phish flawless, while LLM-powered apps opened a new bug class entirely. What actually changed, and what still works.
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.
Prompt Injection in CI/CD Pipelines: Attack Paths and Defenses
When LLMs review PRs, triage issues, and fix builds, every commit message becomes attacker input. The concrete attack paths through GitHub Actions and what blocks them.
The OWASP AI Top 10 Explained: LLM Risks for 2025 and Beyond
The OWASP AI Top 10 is the community list of the most critical security risks in LLM applications, led by prompt injection. Here is what each entry means and how to defend against it.
Prompt Injection as a Supply Chain Risk: When AI Dependencies Are Exploitable
Prompt injection is not just an application vulnerability. When LLMs process content from the software supply chain -- package descriptions, README files, commit messages -- injection becomes a supply chain attack vector.
Jailbreaking AI: How LLM Jailbreaks Work and How to Defend Against Them
Jailbreaking AI means getting a model to bypass its own safety guardrails. This guide explains how jailbreaks work conceptually, how they differ from prompt injection, and how to build layered defenses.
Prompt Injection Defences: Griffin AI vs Mythos
Prompt injection is the defining AI security problem of this generation. The defences are structural, not cosmetic — and the architectural choices show.
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.