CVE-2026-96620
— UNSCOREDpublic exploit availablePublished 2026-10-16 · Updated 2026-10-16
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD description
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.
Weaknesses
CWE-20, CWE-78, CWE-88
Public exploit & PoC references
- https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662
- https://github.com/anthropics/claude-agent-sdk-python/pull/1123
- https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121
- https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm
All references
- https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662
- https://github.com/anthropics/claude-agent-sdk-python/pull/1123
- https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121
- https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2026-105788PoC
- UNSCOREDCVE-2026-107734PoC
- HIGHCVE-2026-16793
- HIGHCVE-2026-86022PoC
- HIGHCVE-2026-86035PoC
- HIGHCVE-2020-37279PoC
- CRITICALCVE-2020-37282PoC
- HIGHCVE-2022-51019PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.