Cyber AI Digest

November 3, 2026

  1. Adversa Nov 3, 2026
    Synapse Halo mascot - News

    News

    Cursor incidents caused damage without exploiting a published Cursor CVE.

    • The confirmed damage notably goes through extensions and project files that the agent trusts.

    • In October 2026, the Cursor marketplace distributed a booby-trapped Claude Code extension for about 11 hours.

    • At PocketOS, an agent deleted a production volume with a Railway token found in a file.

    • Workspace Trust is disabled by default, letting a .vscode/tasks.json task run when a folder is opened.

    Read the original article Cursor security: top 10 attacks and what each one actually broke adversa.ai

  2. Signals Corps Nov 3, 2026
    Synapse Halo mascot - News

    News

    SEP-2640 lets MCP servers distribute skills to AI agents.

    • In late October 2026, almost no current client loaded these skills distributed by MCP.

    • The checks confirm the consistency of the files, but not the reliability of their instructions.

    • The specification requires the client to ask the user's consent before running code linked to a skill.

    • A local MCP server or a manipulated agent can already drop a skill into a trusted folder.

    Read the original article Are you ready for the MCP Skills Extension (SEP-2640)? signalscorps.com

  3. Oktsec Nov 3, 2026
    Synapse Halo mascot - News

    News

    AI agents with overly broad rights can amplify existing security weaknesses.

    • The NCSC's 2026 annual review lists 337 incidents that required its support.

    • In the incidents handled, no observed use of AI enabled a new category of attack.

    • The NCSC invites examining accessible data, tools, trusted instructions and control of actions.

    Read the original article NCSC Annual Review 2026: lessons for AI agent security oktsec.com