CVE-2026-54316: Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch
Advisory generated from the CVE record, CISA, Exploit Observer and VEDAS: what it is, whether it is exploited, who is affected, and how to fix and detect it.
Generated by VEDAS. Scores as of 2026-11-01 19:19 UTC. Rebuilt every few hours from cve-scores, CISA KEV and vedas-signatures. How this works and its limits.
What it is
Claude 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.
Description quoted from the CVE record (assigned by GitHub_M, published 2026-06-23).
Weakness: CWE-183: Permissive List of Allowed Inputs; CWE-200: Exposure of Sensitive Information to an Unauthorized Actor; CWE-515: Covert Storage Channel
How it can be exploited
Exploitable over the network with low attack complexity only when specific conditions are present needing no privileges and a user must take an action. Impact: confidentiality high, integrity none, availability none. CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
CISA assessment (SSVC): CISA has no evidence of exploitation. Automatable: no. Technical impact: partial.
Public exploit evidence (Exploit Observer)
Also known as: EUVD-2026-38538, GHSA-fg94-h982-f3mm
Exploit Observer links 1 piece of public exploit code or detection modules that name this CVE or one of its aliases.
Exploit code and modules (1)
Code that names this CVE. A repository can be a working exploit, a scanner, a fake or malware; read it before running anything.
- Code repository: https://github.com/inertfluid/cve-2026-54316-lab
Vulnerability databases and vendor advisories (5)
Catalogue entries, not exploit evidence.
- Vulnerability database or vendor advisory: https://euvd.enisa.europa.eu/enisa/EUVD-2026-38538
- Vulnerability database or vendor advisory: https://github.com/advisories/GHSA-fg94-h982-f3mm
- Vulnerability database or vendor advisory: https://nvd.nist.gov/vuln/detail/CVE-2026-54316
- Vulnerability database or vendor advisory: https://osv.dev/vulnerability/CVE-2026-54316
- Vulnerability database or vendor advisory: https://osv.dev/vulnerability/GHSA-fg94-h982-f3mm
VEDAS data as of 2026-11-01T17:12 UTC; fetched 2026-11-02.
Live scores
- EPSS
- 0.005
low predicted chance of attack - VEDAS
- 0.055
little exploit evidence - On CISA KEV
- Not listed
- Detection rule
- None yet
Thin horizontal line: the “likely” (EPSS 0.10) or “strong” (VEDAS 0.90) threshold. Shaded “no data” areas are periods when cve-scores did not publish.
Who is affected
| Product | Affected | Not affected |
|---|---|---|
| anthropics claude-code | version >= 0.2.54, < 2.1.163 | Not stated |
Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.
Exploit Observer also maps it to: anthropic claude_code.
How to fix it
No fixed version or vendor advisory is listed in the CVE record yet. Watch the vendor’s security page.
How to detect it
There is no open VEDAS detection rule for this bug yet. It is listed on the detection gaps page if CISA has confirmed attacks.
Advisories on this CVE
- AI coding agents in CI: one GitHub issue can reach your secrets (full advisory)
- AI coding agents in CI: one GitHub issue reaches secrets (Novee, Black Hat USA, 5 Aug 2026) (5 Aug 2026)
- Claude Code 2026 CVEs (3 Apr 2026)
References
Other references
- https://github.com/anthropics/claude-code/security/advisories/GHSA-fg94-h982-f3mm (x_refsource_CONFIRM)
Other databases
Where this comes from
This advisory is generated automatically by VEDAS from: CVE.org record, cve-scores (EPSS and VEDAS), Exploit Observer. Text in quotes is reproduced from the source; everything else is a fixed template filled with source fields. Nothing here is written by a language model. Check the vendor advisory before acting, and read how VEDAS and Exploit Observer work, and their limits.