cve.bz

CVE-2026-54316 anthropic claude code: Permissive List of Allowed Inputs

6.0 mediumEPSS 0.5%Fix available

Medium (6.0) in anthropic claude code. EPSS 0.5% estimated probability of exploitation activity in the next 30 days. Fixed in @anthropic-ai/claude-code 2.1.163.

On this page
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.

Severity

CVSS 4.0

6.0 medium
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

CVSS 3.1

9.1 critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
EPSS
0.5% (unchanged from 0.5% a week ago; 0.5% 30 days ago) estimated probability of exploitation activity in the next 30 days; 45th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: no · Technical impact: partial, assessed 2026-06-23. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-183 Permissive List of Allowed Inputs
CWE-200 Exposure of Sensitive Information to an Unauthorized Actor
CWE-515 Covert Storage Channel
OWASP Top 10
A01:2025 Broken Access Control, A06:2025 Insecure Design
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

  • @anthropic-ai/claude-code (npm): fixed in 2.1.163

Ask an AI about this CVE

Show the promptExplain CVE-2026-54316 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-54316?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-54316?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-54316 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
anthropic:claude_codefrom 0.2.54 before 2.1.163

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-fg94-h982-f3mmnpm@anthropic-ai/claude-code>=0.2.54 <2.1.1632.1.163

Red Hat

Red Hat rates this Moderate.

Red Hat's statement

A flaw was found in Claude Code versions 0.2.54 through 2.1.162, where the hostname huggingface.co was pre-approved for the WebFetch tool without path restrictions. An attacker who could inject untrusted content into a Claude Code context window could direct it to make WebFetch requests to attacker-controlled HuggingFace repository files, creating a covert out-of-band channel for exfiltrating data accessible to the Claude Code session. Red Hat OpenShift Dev Spaces ships claude-code version 2.1.138 in its plugin registry container.

Red Hat's mitigation

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.

ProductPackageStateAdvisory
Red Hat OpenShift Dev Spacesdevspaces/pluginregistry-rhel9Fix deferred

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-54316.

GitHub PoC

Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it. How Harbor Check reads them, and what it found.

  • InertFluid/cve-2026-54316-lab Harbor Check: matches CVE 1 star, Shell, created
    Reproduction lab for CVE-2026-54316 (Claude Code WebFetch huggingface.co bare-hostname permission bypass / exfiltration)

Attack patterns (CAPEC)

  • CAPEC-3 Using Leading 'Ghost' Character Sequences to Bypass Input Filters Likelihood: Medium · Severity: Medium
  • CAPEC-43 Exploiting Multiple Input Interpretation Layers Likelihood: Medium · Severity: High
  • CAPEC-71 Using Unicode Encoding to Bypass Validation Logic Likelihood: Medium · Severity: High
  • CAPEC-120 Double Encoding Likelihood: Low · Severity: Medium

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-200 (59).

References

Check your stackJSON