Labels

• bug

  Something isn't working
• documentation

  Improvements or additions to documentation
• duplicate

  This issue or pull request already exists
• enhancement

  New feature or request
• feedback

  Community feedback on a specific entry
• good first issue

  Good for newcomers
• help wanted

  Extra attention is needed
• invalid

  This doesn't seem right
• LLM01

  LLM01 Prompt Injection
• LLM02

  LLM02 Sensitive Information Disclosure
• LLM03

  LLM03 Supply Chain
• LLM04

  LLM04 Data and Model Poisoning
• LLM05

  LLM05 Improper Output Handling
• LLM06

  LLM06 Excessive Agency
• LLM07

  LLM07 System Prompt Leakage
• LLM08

  LLM08 Vector and Embedding Weaknesses
• LLM09

  LLM09 Misinformation
• LLM10

  LLM10 Unbounded Consumption
• question

  Further information is requested
• sprint-2

  Sprint 2 — Community Review and Voting (May 4–18, 2026)
• TB-CFAS

  Compositional Fine-Tuning Alignment Subversion
• TB-CMSB

  Cross-Modal Safety Bypass
• TB-ITSC

  Inference-Time Side-Channel Disclosure
• TB-MCPX

  MCP Tool Interface Exploitation
• TB-MMIS

  Model Misalignment
• TB-MSDA

  Model Scheming and Deceptive Alignment
• TB-SICG

  Systemic Insecure Code Generation
• TB-WLLA

  Weaponized LLM Abuse
• track-a

  Track A — feedback on existing Top 10 entries
• track-b

  Track B — feedback on new candidate entries