prompt injection
IBM Releases LLMON Markup and Two Granite 4.1 Preview Models
IBM has released LLMON and two Granite 4.1 preview models, calling them an experimental preview that is not for production.
Just in
Latest
AI Agent Security, 8 October (Evening): Disputed AgentCore Research, Claude Code’s Fail-Closed Hooks and Malware Aimed at AI Analysts
Three agent-security stories from 8 October. Zenity says one prompt to an exposed AWS AgentCore agent could lead to control of every agent in the same account and region, and AWS disputes it. Claude Code adds an option that blocks an action when a safety hook fails. Cisco Talos finds malware that writes to AI analysts. What each shows, and what it does not.
AI Agent Security: Langflow Flaw, Copilot CLI Finding, New Guardrails
A critical Langflow flaw let MCP server settings run any command. Researchers say GitHub's Copilot CLI followed encrypted instructions that it refused in plain text; GitHub says that is not a vulnerability. Meanwhile Atlassian has split its 220+ agent tools into read, write and destructive tiers, and OpenAI has made Codex Auto-review free. What each one confirms.
Timeline
Every story in prompt injection, grouped by month.
November 2026
- 13 Nov 2026: IBM Releases LLMON Markup and Two Granite 4.1 Preview ModelsIBM has released LLMON and two Granite 4.1 preview models, calling them an experimental preview that is not for production.
October 2026
- 15 Oct 2026: Quick Guide: Build a Claude Code Second Brain With Google and NotesOne X user's recipe joins Claude Code, Google's gws CLI, Graphify and Playwright into a "second brain". How to set it up, and the…
- 12 Oct 2026: GitLab Patches CVE-2026-97229, a CVSS 10.0 Flaw That Could Let an Unauthenticated User Run Code Through a Crafted CI/CD RegexGitLab says CVE-2026-97229, a CVSS 10.0 flaw, could let an unauthenticated user run code via a crafted CI/CD regex. Self-managed: upgrade now.
- 10 Oct 2026: Grok Agents, Part 2: Tools, Connectors and Your Own DataPart two of our Grok agent guide: tools, connectors and MCP in plain words, a safe read-only first setup, how to limit access and…
- 10 Oct 2026: What Grok Bot Connects To and What It Can Do Inside Each ServiceWhat Grok Bot connects to, how sign-in and custom MCP connections work, what it can do inside Gmail, Drive, Notion and more, and how…
- 8 Oct 2026: AI Agent Security, 8 October (Evening): Disputed AgentCore Research, Claude Code's Fail-Closed Hooks and Malware Aimed at AI AnalystsThree agent-security stories from 8 October. Zenity says one prompt to an exposed AWS AgentCore agent could lead to control of every agent in…
- 8 Oct 2026: AI Agent Security: Langflow Flaw, Copilot CLI Finding, New GuardrailsA critical Langflow flaw let MCP server settings run any command. Researchers say GitHub's Copilot CLI followed encrypted instructions that it refused in plain…
Related stories
Latest from topics connected to prompt injection. See all with connected topics
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.
