Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration
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.
- Published
- Jul 16, 2026
- Updated
- Jul 18, 2026
- EPSS
- 0.8% · 54th percentile
- CWE
- CWE-78
Sign in to follow · You’ll be notified if a followed record enters KEV, gets an exploit or is updated.
Report tools
Action score
21
Monitor
Low priority for now.
- CVSS
- 21 / 40 · 5.3 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.8%
CISA SSVC decision
- Exploitation
- none
- Automatable
- yes
- Technical impact
- total
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · GitHub_M
- 5.3
- NVD has not scored this yet; the score shown is the CNA’s.
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:L/VA:N/SC:H/SI:H/SA:N
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Affected systems
—
Versions reported by the vendor
Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.
anthropics claude-code-action
- < 1.0.74affected
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| anthropics claude-code-action | 1.0.74 · description | Vendor (CNA) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
No dated events beyond publication.
FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
No credits in the CNA record.
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
No nightly-computed relations.
Chain candidates
An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.
—
Bug bounty scope
No known public program.
Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- A low-privileged account is enough.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- Integrity
- Availability
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
- Scope
- X
Weakness class (CWE)
CWE-78 · Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')CVSS vector
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:L/VA:N/SC:H/SI:H/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
nvd-secondary
Root cause
User input is inserted as text into a shell command. The shell may interpret special characters in the input as part of the command.
The bug in code
The whole CWE-78 classA representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.
Vulnerable
const host = req.body.host;exec("ping -c 1 " + host, onResult);Fixed
const host = req.body.host;if (!/^[a-z0-9.-]{1,253}$/i.test(host)) return res.sendStatus(400);execFile("ping", ["-c", "1", host], onResult);Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- Command Line Execution through SQL InjectionCAPEC-108likelihood: Low · Very High
- Command DelimitersCAPEC-15likelihood: High · High
- Exploiting Multiple Input Interpretation LayersCAPEC-43likelihood: Medium · High
- Argument InjectionCAPEC-6likelihood: High · High
- OS Command InjectionCAPEC-88likelihood: High · High
ATT&CK techniques
—
Noroxi analysis
No Noroxi analysis for this record yet
We don't hand-write analysis for all 385,000+ vulnerabilities; that wouldn't be honest. For notable, high-impact vulnerabilities our team writes the mechanism, detection and remediation steps.
We use this product, ask for helpChange log
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
- github.com/anthropics/claude-code-action/commit/9ddce40de8c1ab71fb6303a125fdad0968dc1312
- github.com/anthropics/claude-code-action/pull/1066
- github.com/anthropics/claude-code-action/releases/tag/v1.0.74
- github.com/anthropics/claude-code-action/security/advisories/GHSA-8q5r-mmjf-575q
Vendor advisories and official records. Exploit/PoC links are deliberately left out.