Critical (9.2) in anthropics claude-agent-sdk-python. EPSS 0.7% estimated probability of exploitation activity in the next 30 days. Fixed in claude-agent-sdk 0.2.121.
Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag to define a stdio MCP server, causing arbitrary command execution at CLI startup outside the SDK permission controls. The issue is exploitable when an application passes untrusted input as the session ID to resume. This issue is fixed in version 0.2.121.
0.7%(unchanged from 0.7% a week ago; 0.6% 30 days ago) estimated probability of exploitation activity in the next 30 days; 54th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: total, assessed 2026-10-21. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-20Improper Input Validation CWE-78Improper Neutralization of Special Elements used in an OS Command (OS Command Injection) CWE-88Improper Neutralization of Argument Delimiters in a Command (Argument Injection)
Show the promptExplain CVE-2026-96620 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-96620?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-96620?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-96620 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.
Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.