ThreatVectr
Tag

#prompt injection

77 stories taggedprompt injection · page 3 of 6.

Full-frame edge-to-edge photoreal overhead shot of a sleek aluminum laptop on a dark desk, screen glowing with abstract hex dump and disassembly patterns in coo
AI Security

One Click Was All It Took to Hijack Anthropic's Claude AI

A flaw in the Claude Desktop app let attackers silently feed malicious instructions to the AI and steal private files. The bug is fixed, but the attack method points to a new category of risk.

3 min read
Photoreal editorial image, full frame 16:9, of a modern open-plan office at dusk with rows of laptops glowing on empty desks, soft blue and amber light, a trans
AI Security

The AI Blind Spot in Corporate Security: Why Old Traffic Inspection Is Falling Behind

Employees are pasting company secrets into ChatGPT and installing rogue browser add-ons. The security tools most firms rely on can't see any of it.

4 min read
Full-frame photoreal editorial image of a dimly lit office desk at night, a laptop open showing a blurred generic email interface, a faint ghostly glow rising f
AI Security

One Poisoned Email Can Rewrite What Your AI Assistant 'Remembers' About You

Researchers show how a single message can plant a false memory in an AI agent's long-term store, quietly steering its answers in every future chat.

4 min read
Full-frame photoreal editorial shot of a dim server room with rows of blinking network equipment, one rack door slightly ajar, a faint blue glow spilling across
Identity & Access

The Week Trusted Software Turned Hostile: ShareFile, Citrix Bleed 2, and AI Coding Attacks

Automated bug-hunting is cutting both ways, and old flaws are still landing hits because patches sat in a queue.

4 min read
Full frame overhead view of a developer's dark wooden desk lit by warm lamp light, a large monitor showing colourful lines of source code with a single PNG thum
AI Security

'Ghostcommit' smuggles hacker instructions inside images to trick AI coding assistants

Researchers hid secret commands in an ordinary PNG file, walked past two popular AI code reviewers, and got a coding assistant to leak a project's passwords.

3 min read
Close-up, edge-to-edge 16:9 photograph of a glowing circuit board with streams of faintly visible text and code cascading across its surface in soft blue and wh
AI Security

CrowdStrike Flags Five New Ways Criminals Can Trick AI Into Obeying Them

Researchers have mapped out a fresh set of prompt injection attacks, where criminals feed deceptive instructions to AI systems to make them behave in harmful ways. Here is what each one does and why ordinary employees are part of the risk picture.

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
A close-up, sharply focused photograph of a glowing laptop screen in a darkened office, showing lines of green and white code reflecting faintly on a glass desk
AI Security

A Hidden Note in a Bug Report Tricked GitHub's AI Into Leaking Company Secrets

Researchers showed how a single crafted message in a public GitHub issue could fool an AI assistant into reading private code and posting it online for anyone to see.

3 min read
Photoreal news-editorial 16:9 image
AI Security

Researchers Show How a Fake GitHub Comment Can Trick AI Tools Into Leaking Secret Code

A crafted public comment on GitHub can manipulate AI-powered automation into handing over data from private repositories, no password required.

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

A Hidden Command in a GitHub Issue Can Silently Steal a Company's Private Code

Researchers found a flaw in GitHub's AI automation tool that lets an outsider read an organisation's private repositories by hiding plain-English instructions inside a public bug report.

3 min read
Photoreal news-editorial 16:9 photograph of a close-up view of a glowing computer screen displaying abstract flowing green and amber data streams, with a physic
AI Security

AI Agents Can Be Tricked Into Sending Money. Zscaler Has the Data.

A new study shows that some expensive, enterprise-grade AI assistants fall for hidden instructions that most humans would ignore, and experts warn the real danger is far bigger than a fake three-dollar fee.

3 min read
A photoreal overhead view of a domestic living room shelf holding a small black streaming box, a home router with blinking lights, and a smartphone, all connect
Threat Intelligence

The Weak Link This Week Wasn't Code. It Was Trust.

From home streaming boxes turned into criminal relays to AI assistants tricked by hidden instructions, this week's incidents share one root cause: systems trusting the wrong thing.

4 min read
Close-up top-down view of a glowing digital web of interconnected nodes on a dark surface, with one node subtly emitting a hidden pulse of light in a different
AI Security

Hackers Are Hiding Instructions Inside Websites to Make AI Assistants Send Crypto Payments

Two newly discovered attack campaigns show how criminals can secretly hijack AI browsing agents by planting hidden commands in ordinary-looking web pages.

3 min read
A close-up top-down view of a mechanical keyboard on a dark desk, its keys softly lit by the cool blue glow of a monitor displaying abstract cascading lines of
Vulnerabilities

Popular AI Coding Tool Cursor Has Flaws That Could Let Attackers Run Code on Your Computer

Security researchers found two vulnerabilities in the Cursor AI code editor that could allow an attacker to silently take control of a developer's machine — no click required.

3 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
© 2026 Threat Vectr