Description
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.
Details
Affected Packages
| Software | From version | Fixed in |
|---|---|---|
| claude-agent-sdk | โ | 0.1.55 |
| claude-code | โ | 2.1.91 |
| unknown | โ | โ |
References
N/ASimilar Threats
- High CVE-2026-35021
- Critical CVE-2026-35022
Site Security Check
Concerned your site may already be targeted?
BotEraser analyzes incoming traffic patterns and helps identify bot behavior consistent with known exploit attempts.
Check My Site Free โNo credit card required ยท Results in minutes
ⓘ Data Notice: The information presented above has been compiled from publicly available internet sources. Boteraser aggregates this data solely for informational purposes and does not independently classify, evaluate, or endorse any findings about the vulnerabilities listed. The accuracy and completeness of this information is the sole responsibility of the original publishers. Boteraser and its operators accept no liability for any decisions made based on this data.