Topic

#Prompt Injection

23 articles on Prompt Injection — news, releases, guides and analysis from the SourceFeed engine.

One Vendor Finally Published the Attacks It Can't Catch

An open benchmark with a public failure list beats unverifiable detection claims — but a self-scored 99.8% still isn't proof.

Ji-ho Choi

Claude's Memory Leak Is Every Agent Builder's Problem

A link-walking exploit shows agentic browsing turns AI memory into a silent data-exfiltration channel by design.

Article · 1mo ago2

GitLost Proves Agentic Workflows Have No Trust Boundary

A single public GitHub issue tricked an AI agent into pasting private repo contents into a comment anyone could read.

News · 1mo ago1

Securing GitHub Agentic Workflows Against the GitLost Exploit

The GitLost vulnerability exposes private repositories through public issues, proving that English-programmed agents require strict, traditional security boundaries.

Article · 1mo ago0

When Seven AI Security Gates All Say LGTM

A viral incident report is pure fiction, but every way its AI defenses fail is already happening in production.

Article · 2mos ago2

Prompt Injection Is the Least of Your AI Security Problems

Real-world attacks reveal that while frontier models can resist linguistic trickery, your glue code and infrastructure are wide open.

Article · 2mos ago1

Why Prompt Injection Works: The Role Confusion Theory

LLMs assign authority based on how text is written, not where it comes from, making role tags a leaky abstraction.

Article · 2mos ago4

Agentjacking: How Public Sentry Keys Turn AI Coding Agents Into Trojan Horses

A newly disclosed exploit chain weaponizes public DSNs and the Model Context Protocol to execute arbitrary code on developer machines.

Article · 2mos ago4