Check Point bypassed ChatGPT Lockdown Mode through HTML previews; OpenAI fixed it in September
A nested iframe in ChatGPT's HTML preview let pages open unsandboxed popups, defeating Lockdown Mode. Zero-click in ChatGPT Classic. Fixed 18 Sept.
Topic · 11 stories
11 stories tagged prompt-injection on AI Tamer, newest first.
A nested iframe in ChatGPT's HTML preview let pages open unsandboxed popups, defeating Lockdown Mode. Zero-click in ChatGPT Classic. Fixed 18 Sept.
Check Point calls it prompt adware: a Codex jailbreak bundle that rewrites agent instructions so a greeting returns an ad for its author's LLM gateway.
SolidCraft 0.30.1 fixes three advisories: an agent permission bypass, a lock-file symlink overwrite and an API key check skipped with '#'. Upgrade now.
A Moderate GHSA in the Rust inference engine: for qwen-xml and gemma4, text a model quotes could be parsed as a second tool call. Fixed in v0.9.5.
Forever Security found an agent instructions file in a customer's Downloads folder. Its tests hijacked Codex and Claude Code. Never start an agent there.
ATT&CK v20, released 13 October, adds Direct and Indirect Prompt Injection, AI-Enabled Exfiltration and AI Result Poisoning to the Enterprise matrix.
In 90 of 6,637 malicious agent skills, VirusTotal found the payload hidden where reviewers don't see it but agents still read it. Here is how to check.
HiddenLayer says a Jev checkout agent gave a planted Confirm Price button 91 percent. The Register says TypeSafe did not immediately reply.
Barracuda describes a phishing email aimed at the person and at the AI assistant that summarizes the inbox. The research gives no count of how widespread the campaign is.
Cisco Talos says malware is embedding plain-language instructions meant to steer AI analysis tools toward a benign verdict. It traces the method across four families and 84 samples from January 2025 through July 2026.
Prompt injection can arrive in a user prompt, web page, file, email or tool result. Build defenses around permissions and actions because text filters cannot reliably stop it.