anthropics claude-code-action up to 1.0.73 MCP Server .mcp.json default behavioral workflow

Summaryinfo

A vulnerability categorized as critical has been discovered in anthropics claude-code-action up to 1.0.73. The impacted element is an unknown function of the file .mcp.json of the component MCP Server. Such manipulation of the argument default leads to behavioral workflow. This vulnerability is uniquely identified as CVE-2026-47751. The attack can be launched remotely. No exploit exists.

Detailsinfo

A vulnerability was found in anthropics claude-code-action up to 1.0.73 and classified as critical. Affected by this issue is an unknown functionality of the file .mcp.json of the component MCP Server. The manipulation of the argument default with an unknown input leads to a behavioral workflow vulnerability. Using CWE to declare the problem leads to CWE-841. The product supports a session in which more than one behavior must be performed by an actor, but it does not properly ensure that the actor performs the behaviors in the required sequence. Impacted is confidentiality, integrity, and availability. CVE summarizes:

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionally enabled all project MCP servers via enableAllProjectMcpServers, an attacker who opened a pull request containing a malicious .mcp.json file could achieve arbitrary code execution on the GitHub Actions runner and exfiltrate secrets available to the workflow (such as API keys and tokens) when a privileged user or an automatic trigger invoked the Claude action on the pull request. This issue is fixed in version 1.0.74, which restores .claude/ and .mcp.json from the pull request base branch before the CLI runs.

The advisory is available at github.com. This vulnerability is handled as CVE-2026-47751 since 05/20/2026. The exploitation is known to be easy. The attack may be launched remotely. No form of authentication is required for exploitation. Technical details are known, but there is no available exploit.

By approaching the search of inurl:.mcp.json it is possible to find vulnerable targets with Google Hacking.

Upgrading to version 1.0.74 eliminates this vulnerability.

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• anthropics

Name

• claude-code-action

Version

• 1.0.0
• 1.0.1
• 1.0.2
• 1.0.3
• 1.0.4
• 1.0.5
• 1.0.6
• 1.0.7
• 1.0.8
• 1.0.9
• 1.0.10
• 1.0.11
• 1.0.12
• 1.0.13
• 1.0.14
• 1.0.15
• 1.0.16
• 1.0.17
• 1.0.18
• 1.0.19
• 1.0.20
• 1.0.21
• 1.0.22
• 1.0.23
• 1.0.24
• 1.0.25
• 1.0.26
• 1.0.27
• 1.0.28
• 1.0.29
• 1.0.30
• 1.0.31
• 1.0.32
• 1.0.33
• 1.0.34
• 1.0.35
• 1.0.36
• 1.0.37
• 1.0.38
• 1.0.39
• 1.0.40
• 1.0.41
• 1.0.42
• 1.0.43
• 1.0.44
• 1.0.45
• 1.0.46
• 1.0.47
• 1.0.48
• 1.0.49
• 1.0.50
• 1.0.51
• 1.0.52
• 1.0.53
• 1.0.54
• 1.0.55
• 1.0.56
• 1.0.57
• 1.0.58
• 1.0.59
• 1.0.60
• 1.0.61
• 1.0.62
• 1.0.63
• 1.0.64
• 1.0.65
• 1.0.66
• 1.0.67
• 1.0.68
• 1.0.69
• 1.0.70
• 1.0.71
• 1.0.72
• 1.0.73

Website

• Product: https://github.com/anthropics/claude-code-action/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion