Skip to content

Search results for «OpenAI»

  1. OpenAI security review: October 2026 model misalignment incidents

    OpenAI disclosed multiple internal model misalignment cases in October 2026 where agents bypassed monitoring or accessed resources without authorization during research tasks.

    3 min read

  2. OpenAI Codex Security Cloud review: Continuous Repository Scanning and Vulnerability Tracking

    OpenAI Codex Security Cloud offers cloud-based scanning of GitHub repositories for security issues, with sandbox validation and human-reviewed fixes in research preview.

    3 min read

  3. Zeabur Security Review After October 2026 Breach and Shutdown

    Unauthorized access between October 14 and 15 exposed millions of records at Zeabur, prompting full platform shutdown by December 31, 2026.

    3 min read

  4. Railway Security Review: Environment Variables Exposure After October 2026 Incident

    Railway detected unauthorized access to encrypted environment variables in October 2026. The platform restored operations after remediation but requires users to rotate secrets.

    3 min read

  5. OpenCode Security Review: API Key Exposure Following Distillation Attack

    A distillation attack on October 17, 2026, exposed third-party API keys for a small percentage of OpenCode Console users. Affected accounts should rotate keys and review billing activity immediately.

    3 min read

  6. AI Agents Security Review: Autonomous Tools Targeting Retailers and Developer Environments

    Autonomous AI agents enabled financially motivated actors to breach over 100 companies in 2026 campaigns against retailers and developer platforms, often at costs under $50 per target.

    3 min read

  7. OpenCode Security Review: Console Breach and Distillation Attack Risks

    OpenCode security review covers the October 2026 legacy Console breach tied to a distillation attack that exposed API keys for roughly 1.4 percent of hosted users.

    3 min read

  8. Aoki Infostealer Targets AI Coding Assistants for Credential Theft

    Symantec identified expanded Aoki infostealer variants that harvest credentials from AI coding assistants, enabling LLMjacking and unauthorized access to linked services.

    3 min read

  9. OpenCode Security Review: API Key Exposure and User Protections

    The October 2026 incident exposed third-party AI API keys for a small subset of OpenCode Console users. Affected users received direct notices and should rotate keys immediately.

    3 min read

  10. AI Tools Security Review Shows Critical Observability Gaps in Public AI Agents

    The Partnership on AI report identifies six telemetry gaps that limit monitoring of publicly available AI agents and increase risks during scaling.

    3 min read