Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version. Thank you to hackerone.com/novee for reporting this issue.
Update @anthropic-ai/claude-code to 2.1.163 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanClaude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch affects @anthropic-ai/claude-code (npm). Severity is critical. Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version. Thank you to hackerone.com/novee for reporting this issue.
AI coding agents often install or upgrade packages automatically in npm. A critical vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version. Thank you to hackerone.com/novee for reporting this issue.
Update @anthropic-ai/claude-code to 2.1.163 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanClaude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch affects @anthropic-ai/claude-code (npm). Severity is critical. Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version. Thank you to hackerone.com/novee for reporting this issue.
AI coding agents often install or upgrade packages automatically in npm. A critical vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
| Package | Affected range | Fixed version |
|---|
| @anthropic-ai/claude-codenpm | >=0.2.54,<2.1.163 | 2.1.163 |
|---|
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL Guard| Package | Affected range | Fixed version |
|---|
| @anthropic-ai/claude-codenpm | >=0.2.54,<2.1.163 | 2.1.163 |
|---|
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL Guard