58 matches found
CVE-2026-96620
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, causin...
agent-framework-claude (>=1.0.0b260319, <=1.0.0b260521), agent-webkit-server (>=0.1.0, <=0.2.0) +43 more potentially affected by CVE-2026-96620 via claude-agent-sdk (>=0.1.20, <=0.2.120)
claude-agent-sdk PYPI version =0.1.20, =1.0.0b260319, =0.1.0, =0.1.0, =0.1.0, =8.1.0, =0.3.12, =0.3.0, =0.4.0, =0.1.12, =0.4.3, =0.1.0, =0.1.2 - expluro 0.9.0 - glyph-agents 0.3.0 - gobby 0.3.4 - home-agent 0.1.1 and more Source cves: CVE-2026-96620 Source advisory: GHSA-H4MW-J7QP-8MWM...
GHSA-H4MW-J7QP-8MWM Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
The Claude Agent SDK for Python passed the resume option to the Claude CLI without validation, allowing a value beginning with - to be interpreted as a separate CLI flag. An attacker who controlled the resume value could inject an --mcp-config flag defining a stdio MCP server, resulting in...
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
The Claude Agent SDK for Python passed the resume option to the Claude CLI without validation, allowing a value beginning with - to be interpreted as a separate CLI flag. An attacker who controlled the resume value could inject an --mcp-config flag defining a stdio MCP server, resulting in...
agent-framework-claude (>=1.0.0b260319, <=1.0.0b260521), agent-webkit-server (>=0.1.0, <=0.2.0) +43 more potentially affected by CVE-2026-96620 via claude-agent-sdk (>=0.1.20, <=0.2.120)
claude-agent-sdk PYPI version =0.1.20, =1.0.0b260319, =0.1.0, =0.1.0, =0.1.0, =8.1.0, =0.3.12, =0.3.0, =0.4.0, =0.1.12, =0.4.3, =0.1.0, =0.1.2 - expluro 0.9.0 - glyph-agents 0.3.0 - gobby 0.3.4 - home-agent 0.1.1 and more Source cves: CVE-2026-96620 Source advisory: OSV:GHSA-H4MW-J7QP-8MWM...
CVE-2026-96620 Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
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, causin...
CVE-2026-96620
The Claude Agent SDK (a Python SDK for Claude Code) is vulnerable to argument injection in versions prior to 0.2.121 . The root cause is the lack of validation on the resume option , where a dash-leading value is incorrectly parsed as an independent CLI flag. An attacker providing untrusted input...
EUVD-2026-103155
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, causin...
CVE-2026-96620 Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
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, causin...
CVE-2026-96620
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, causin...
agent-framework-claude (>=1.0.0b260319, <=1.0.0b260521), agent-webkit-server (>=0.1.0, <=0.2.0) +43 more potentially affected by CVE-2026-96620 via claude-agent-sdk (>=0.1.20, <=0.2.120)
claude-agent-sdk PYPI version =0.1.20, =1.0.0b260319, =0.1.0, =0.1.0, =0.1.0, =8.1.0, =0.3.12, =0.3.0, =0.4.0, =0.1.12, =0.4.3, =0.1.0, =0.1.2 - expluro 0.9.0 - glyph-agents 0.3.0 - gobby 0.3.4 - home-agent 0.1.1 and more Source cves: CVE-2026-96620 Source advisory: MEND:CVE-2026-96620...
CVE-2026-96620 Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
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, causin...
CVE-2026-96620: Improper Input Validation
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, causin...
PT-2026-116154
Name of the Vulnerable Software and Affected Versions Claude Agent SDK versions prior to 0.2.121 Description An issue exists where the resume option is passed to the Claude CLI as a separate token without validation. This allows a value starting with a dash to be parsed as an independent CLI flag...
Anthropic Claude Agent SDK for Python: Input validation vulnerability
The Anthropic Claude Agent SDK for Python versions prior to 0.2.121 contain security vulnerabilities. These vulnerabilities stem from the resumption option being passed as an independent token to the Claude CLI without verification. Values starting with a dash are interpreted as independent CLI...
BIT-GITLAB-2026-18252 Inclusion of Functionality from Untrusted Control Sphere in GitLab
GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...
CVE-2026-18252
GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...
CVE-2026-18252 Inclusion of Functionality from Untrusted Control Sphere in GitLab
GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...
EUVD-2026-66428
GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...
CVE-2026-18252 Inclusion of Functionality from Untrusted Control Sphere in GitLab
GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...