ATR-2026-00127mediumSkill Compromiseexperimental
Subcommand Overflow Bypass
Detects SKILL.md files declaring an excessive number of subcommands or tools (>50). Claude Code has a security architecture where each subcommand is individually evaluated for safety. When a skill declares >50 subcommands, some implementations skip security checks on overflow commands due to performance budgets or fixed-size buffers. Attackers pad with 49 benign commands then add malicious ones at the end, expecting the security check to be skipped. Discovered via Claude Code leak analysis (2026-03).
嚴重度
medium
類別
Skill Compromise
掃描目標
skill
作者
ATR Community
建議回應
alert
參考資料
OWASP Agentic
ASI02:2026 - Excessive Agent Autonomy
OWASP LLM
LLM07:2025 - System Prompt Leakage