Safeguard
Tag

LLM

Safeguard articles tagged "LLM" — guides, analysis, and best practices for software supply chain and application security.

40 articles

AI Security

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.

Apr 12, 20267 min read
AI Security

The Limits of Single-Model Vulnerability Scanning: A Technical Analysis of the Mythos Approach

Anthropic's Mythos model claims to find vulnerabilities in open-source code using a single LLM. We analyze where this approach falls short and why production-grade zero-day discovery requires Safeguard's Multi-Agent TAOR Deep Think AI Engine.

Apr 10, 202610 min read
AI Security

Why LLM-Based Vulnerability Scanning Needs More Than a Single Model

Large language models are being used to find vulnerabilities in open-source code. But a single model, no matter how capable, isn't enough. Here's why multi-agent orchestration, structured CWE analysis, and deep context matter more than model size.

Apr 10, 202611 min read
AI Security

LLM Traces and Evals: The Missing Layer in AI Supply Chain Security

Prompt traces and offline evals are standard hygiene for ML teams, but almost nobody treats them as supply chain telemetry. They should be. Here's how traces and evals plug into SBOM and reachability as a fourth security signal.

Apr 8, 20267 min read
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
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
AI Security

LLM-Augmented Bug Discovery Methodology

A practitioner's methodology for using LLMs to augment — not replace — traditional bug discovery workflows, with patterns that hold up under real review load.

Mar 30, 20269 min read
AI Security

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.

Mar 20, 20267 min read
AI Security

How to Use AI for Stock Trading (and the Risks Nobody Mentions)

Using AI for stock trading means applying models to signals, screening, and execution, but the security and reliability risks are as important as the strategy. Here is a grounded look.

Mar 18, 20266 min read
Software Supply Chain Security

Typosquatting Meets AI: The New Threat of AI-Generated Package Names

AI code assistants recommend packages that do not exist, and attackers are registering those hallucinated names. This new typosquatting vector exploits the trust developers place in AI suggestions.

Mar 13, 20267 min read
AI Security

Security Testing for LLM-Powered Applications

Applications built on large language models introduce novel attack surfaces that traditional security testing does not cover. This guide addresses the specific testing methodologies needed for LLM applications.

Mar 12, 20267 min read
AI Security

The Full Form of MCP: What Model Context Protocol Means for Security

The full form of MCP is Model Context Protocol, the open standard that lets AI models talk to tools and data. Here is what it is and where the security risks live.

Mar 11, 20266 min read

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.

LLM (Page 2) — Safeguard Blog