@anthropic-ai/claude-code
Affected
- introduced
0.2.54, fixed2.1.163(semver)
Fixed versions
2.1.163
Fix
- Fixed version
2.1.163npm install @anthropic-ai/[email protected]
Advisory
Also known as: CVE-2026-54316
Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch
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.
Medium Basis: The source's own band: MODERATE
0.2.54, fixed 2.1.163 (semver)2.1.163
2.1.163npm install @anthropic-ai/[email protected]Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0