Latest
●Prompt injection turns up in website HTTP headers, study finds●Nezha dashboard can be crashed by any low-privilege member●MCP Python SDK kept sessions forever, letting memory run out●Nginx UI flaws let MCP tools skip config security checks●Bank of America adds 1,000 contractors to fix Mythos-found bugs●UK stops short of AI rules in Cyber Security Bill●GhostAction campaign hits 1,900 GitHub accounts and 30,000 repos●Attackers target critical Langflow flaw in 1,423 exploit attempts
Friday, 16 October 2026
1 agent hack today▼ 7 vs yesterday (8)
The Agentic TimesPowered byVortal

Incident database

Researchers show prompt injection can hijack TypeSafe AI's Jev decision model

Security firm HiddenLayer demonstrated that TypeSafe AI's Jev 'decision model' and a tuned Qwen3.8-27B model can both be manipulated via indirect prompt injection, hijacking a browser agent's checkout actions in a simulated online store and bypassing prompt verification using a tokenbreak-style attack.

Occurred 15 October 2026 · Disclosed 15 October 2026 · Record updated 15 October 2026

Impact

In a controlled test, researchers consistently hijacked a browser agent's click actions during a simulated checkout process and bypassed prompt verification filters; no real users or production systems were affected.

Our coverage

Sources

  1. theregister.comhttps://theregister.com/ai-and-ml/2026/10/15/jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection/5303184