ThreatVectr
Tag

#Claude Code

12 stories taggedClaude Code.

Aerial top-down view of a large grid of glowing circuit nodes arranged in a 10x10 pattern on a dark surface, some nodes lit amber and red indicating risk levels
AI Security

GhostJacking: How Hackers Can Turn an AI Assistant Against Its Own Company

Researchers showed that a single blocked web request, already sitting in a firewall log, was enough to trick an AI agent into handing over a company's entire domain. Here is what that means for organisations using AI tools to manage their systems.

5 min read
Full-frame photoreal editorial shot of a developer workstation at night, two large monitors filled with code and a security dashboard showing red alert badges,
AI Security

Poisoned AI instruction files are turning developer tools into silent data thieves

Security researchers found real examples on GitHub where configuration files for AI coding assistants were quietly stealing passwords, API keys, and entire conversations, without triggering a single security alarm.

5 min read
Aerial view of a vast modern highway interchange at dusk, concrete lanes splitting and merging with precision, motion-blur streaks of vehicle lights tracing pat
AI Security

The 'RufRoot' Flaw: Why Patching Alone Won't Fix This AI Security Hole

A perfect-severity bug in the Ruflo AI platform let anyone walk in without a password, steal credentials, and quietly poison the system's memory, and the poisoning can linger even after the patch is applied.

3 min read
A computer screen displaying malicious code, symbolizing a sophisticated cyber attack, in an office setting
AI Security

Critical Flaw in Ruflo AI Harness Lets Anyone Run Commands on Your Server

A maximum-severity bug in the open-source Ruflo tool, used with Claude Code and Codex, scores a perfect 10.0 and needs no login to exploit.

3 min read
A close-up, sharply focused 16:9 editorial photograph of a developer's keyboard and monitor in a dimly lit office at night
AI Security

GhostApproval: Six AI Coding Tools Were Tricking Developers Into Approving Dangerous Actions

A new attack pattern shows that the 'human approval' step built into AI coding assistants can be fed false information by the very tool it is supposed to oversee.

3 min read
Photoreal news-editorial photograph, 16:9 framing, full-frame edge-to-edge composition
AI Security

AI Coding Assistants Fooled by Decades-Old File Trick to Attack Developer Machines

A technique as old as Unix itself let researchers plant hidden traps inside innocent-looking code projects, then watch AI tools quietly rewrite the wrong files while developers clicked 'approve'.

3 min read
Full-frame overhead shot of a developer's dark wooden desk, a laptop screen glowing with abstract lines of code, a small red warning icon reflected on the keybo
AI Security

AI Coding Assistants Can Be Tricked Into Running the Very Malware They Were Asked to Find

A proof-of-concept from the AI Now Institute shows Claude Code and OpenAI's Codex executing attacker-supplied code when asked to review it in autonomous mode.

3 min read
Full-frame photoreal editorial shot of a modern developer workstation at dusk, two large monitors glowing with abstract code editor windows, a small permission
AI Security

A trick in six AI coding helpers lets a poisoned project hijack your laptop

Researchers at Wiz found that popular AI coding assistants, including Amazon Q Developer and Claude Code, can be fooled into writing to sensitive files while asking permission for a harmless one.

3 min read
Full-frame photoreal editorial shot of a developer workstation at night, two large monitors filled with code and a security dashboard showing red alert badges,
AI Security

When your AI coder looks exactly like a hacker to the security software

Sophos found that popular AI coding assistants keep tripping the same alarms designed to spot break-ins, and the false alerts are piling up.

4 min read
Macro photograph of a glowing computer terminal screen in a dark room displaying cascading green lines of code and error log text, with a single line subtly hig
AI Security

A Fake Error Message Hijacked AI Coding Assistants — and Security Tools Saw Nothing

Researchers planted a single bogus bug report in a popular developer service and watched AI coding agents obediently run the attackers' code. No password stolen. No alarm raised.

3 min read
AI Security

Poisoned Repos Can Trick Claude Code Into Opening a Reverse Shell

Researchers show that prompt injection hidden inside a repository's files is enough to turn Anthropic's agentic coding tool against the developer running it.

2 min read
AI Security

One GitHub Issue Was Enough to Pwn Repos Running Claude Code Action

A bug in Anthropic's Claude Code GitHub Action turned issue triage into arbitrary code execution — including, briefly, against the action's own repo.

2 min read
© 2026 Threat Vectr