CVE-2026-54316
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedClaude Code is an agentic coding tool. From 0.2.54 until 2.1.163, 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. This vulnerability is fixed in 2.1.163.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceClaude Code's WebFetch tool had a flaw where huggingface.co was pre-approved as a bare hostname, allowing any path on that domain to be accessed without user permission prompts or --allowedTools restrictions. This enabled attackers to use attacker-controlled HuggingFace model repositories as a covert exfiltration channel for data accessible to Claude Code (files, env vars, command output).
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data>= 0.2.54, < 2.1.163CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- None
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Check Claude Code versionRun 'claude --version' or check the installed Claude Code binary versionAffected if version is >= 0.2.54 and < 2.1.163
-
Verify WebFetch tool availabilityCheck if WebFetch is among available tools in your Claude Code instanceAffected if WebFetch tool is enabled and usable
-
Confirm huggingface.co access behaviorTest that huggingface.co URLs can be fetched without explicit permission promptsAffected if WebFetch allows accessing any path on huggingface.co without triggering permission prompts or respecting --allowedTools restrictions
You are affected if Claude Code version is 0.2.54 or higher but lower than 2.1.163 AND the WebFetch tool is enabled and can access huggingface.co URLs without permission prompts.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped2.1.163
Upgrade Claude Code to version 2.1.163 or later, which contains the fix for this vulnerability.
2.1.163 or later
- Check current Claude Code version by running `claude --version` or checking the application info
- Backup any important Claude Code configurations, workspaces, or data if desired
- Upgrade Claude Code to version 2.1.163 or later. Use the appropriate package manager or installation method (e.g., `npm update -g @anthropic-ai/claude-code`, `pip install --upgrade anthropic`, or download the latest release from the official source)
- Verify the upgrade was successful by running `claude --version` and confirming the version is >= 2.1.163
- Confirm the WebFetch tool now properly enforces permission prompts for huggingface.co paths
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation1.0 h
- Implementation1.0 h
- Testing1.0 h
- Review / QA1.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $1,200.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-54316 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-54316 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data