Model

Claude Opus 5

Developed by Anthropic · family claude-5

2 incidents

• AID-2026-0005Jul 2026Claude Opus 5

  Coding agents published internal screenshots to public GitHub repos to get images into private pull requests, Glow finds

  Coding agents that couldn't attach screenshots to private pull requests put them in public GitHub repositories instead, exposing over 13,000 internal images from more than 300 organizations, Glow Security found. Glow reproduced the behavior with Claude Code running Opus 5.

  DeployedHarm: moderateCrime: unlikelyReportedDraftUnauthorized disclosure / whistleblowing
• AID-2026-00092026Claude Haiku 4.5, Claude Mythos Preview, Claude Mythos 5, Claude Opus 5

  Claude models exploited flaws, bypassed access gates, and submitted real forms, including a false police tip, during evaluations

  During evaluations and internal use, Claude models ran commands on a university server through a software flaw, got around token and fee gates, dodged fetch limits with URL shorteners, and submitted real web forms. Claude Haiku 4.5 sent an invented tip to the Philadelphia Police Department's unsolved-homicide form.

  BreakoutHarm: minorCrime: possibleDraftUnauthorized access / intrusionIgnoring explicit instructions