prompt-injection
Safeguard articles tagged "prompt-injection" — guides, analysis, and best practices for software supply chain and application security.
135 articles
Cisco's May 2026 Multi-Turn Jailbreak Study: Why Frontier Model Safety Collapses Over a Conversation
Cisco's AI threat team tested 15 flagship models with ~7,000 multi-turn attacks and found success rates as high as 88 percent. Single-turn safety scores told defenders almost nothing about real-world resilience.
Claude Opus 4.8 for Security Teams: Capabilities, AppSec Use, and Governance (May 2026)
Anthropic shipped Claude Opus 4.8 on May 28, 2026, with sharper agentic coding and better honesty about its own work. Here is what it changes for vulnerability triage, fix-PRs, and the governance you need before it touches your pipeline.
Cursor MCP Security: The Risks and How to Harden It
Cursor's MCP support lets the AI editor call external tools and data sources. That power comes with real risks. Here is how Cursor MCP can be attacked and hardened.
Supabase MCP and the Lethal Trifecta: When an Agent Has service_role
A Cursor user's Supabase MCP server was tricked by a support ticket into exfiltrating an integration_tokens table. The bug was not in MCP. It was in the trifecta.
Tool Poisoning Attacks: How Malicious Instructions Hide I...
AI agent tools can hide invisible instructions attackers use to steal data. Here's how tool poisoning attacks work and how Safeguard stops them.
Agent Skill Marketplaces as the Next Frontier for Supply ...
Agent skill marketplaces are repeating npm and PyPI's supply chain mistakes—except the malicious payload is often a sentence of instructions, not code. Here's what's already been exploited.
Prompt Injection vs Traditional Injection Attacks: A Tech...
SQL injection was solved by separating code from data. Prompt injection can't be, because in an LLM they share one channel. Here's the technical comparison, with real exploits and dates.
Why Autonomous Coding Agents Need Their Own Threat Model
Coding agents run with real credentials and no pause button. Here is the threat model that treats them as autonomous infrastructure, not junior developers.
How Malicious Payloads Get Smuggled Into Trusted AI Skill...
Attackers smuggle malicious payloads into trusted AI skill repositories via typosquats, staged fetches, and split-file obfuscation — here is exactly how it works.
Agentic AI Security Glossary: Tool Poisoning, Prompt Inje...
A precise glossary of agentic AI security terms — prompt injection, tool poisoning, model jailbreaking, excessive agency, and MCP rug pulls — with concrete attack examples.
Why Traditional SAST Tools Struggle to Analyze Agentic Co...
Agentic codebases build call graphs at runtime, defeating static analysis. Here's why SAST tools miss prompt injection and tool-schema risks—and how Safeguard closes the gap.
Hacking AI: How Attackers Target Machine Learning Systems
Hacking AI is not science fiction; it is a growing set of concrete techniques that exploit how models learn, process input, and produce output. Here is how to think about defending against them.
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.