[Bug] False positive security classification triggering mid-session model downgrade during adversarial code review

Related Claude Code issues

Matched on shared title terms, labels, topic and reported release — ranked so issues with real discussion come first.

• [Bug] Anthropic API Error: Safety Filter False Positive Triggering Model Downgrade
  Open 💬 0 v2.1.207 #77166
• [Feature Request] Adversarial code review mode for local codebases
  Open 💬 0 v2.1.223 #84859
• [Bug] Adversarial code review request rejected by safety filters
  Resolved 💬 1 v2.1.170 #67703
• Feature request: fresh-context adversarial plan-review in plan mode (audit before ExitPlanMode)
  Resolved 💬 1 #73515
• [Bug] Incorrect Issue Classification
  Resolved 💬 1 v2.1.170 #77096
• [Bug] BMad `/bmad-code-review` subagent execution fails with adversarial review skill
  Open 💬 1 v2.1.211 #78279
• [Bug][cyber] Safeguard blocked authorized adversarial security review of own web app (req_011CccKEuYAYEFLEtJo1Vn4L)
  Resolved 💬 3 #73057
• [Bug] Subagent returned adversarial security payload instead of code review result
  Open 💬 1 v2.1.206 #76819

Browse by topic

Browse all Claude Code issue topics →