Argument Injection in Claude Agent SDK via --resume Allows Arbitrary Command Execution
Security Advisory
High
Anthropic
Affected:
- claude-agent-sdk < 0.2.121
Fixed in:
- 0.2.121
Referenced CVEs:
CVE-2026-96620 · 9.2
文章内图片已隐藏以节省流量 · Upgrade to Pro to view images & offline archive
This content was auto-fetched from github.com, cleaned by our LLM pipeline, and translated to English. View original.