How severe is CVE-2026-54316?

No CVSS score has been assigned to CVE-2026-54316 yet. Review the advisory details and affected package list to assess your exposure.

Which packages are affected by CVE-2026-54316?

CVE-2026-54316 affects the following packages: @anthropic-ai/claude-code (npm). Ecosystems affected: npm.

How do I fix CVE-2026-54316?

Update @anthropic-ai/claude-code to 2.1.163 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-54316 is resolved across your whole dependency graph.

How do I detect CVE-2026-54316 in my npm dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

How do I mitigate CVE-2026-54316 if there is no patch (or I can't update yet)?

Assume what was exposed is already known: rotate any credential, token or key that the affected component could return, restrict the endpoint to callers that genuinely need it, and strip sensitive fields from responses and error output at the boundary rather than relying on the client not to read them.

Is CVE-2026-54316 actively exploited in the wild?

No public exploit code has been indexed for CVE-2026-54316 yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for CVE-2026-54316?

CVE-2026-54316 has an EPSS (Exploit Prediction Scoring System) score of 0.5%, placing it in the 42th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

What type of vulnerability is CVE-2026-54316?

CVE-2026-54316 is classified as CWE-183 (CWE-183), Information Exposure (CWE-200), CWE-515 (CWE-515). These weakness types describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation.

When was CVE-2026-54316 published, and has it been updated?

CVE-2026-54316 was published on June 23, 2026 and was last updated on August 12, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

CVE-2026-54316: @anthropic-ai/claude-code

Exploitation Status

No confirmed exploitation observed yet

CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-54316.

EPSS Exploitation Probability

via FIRST.org ↗

0.5%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs42th percentile — riskier than 42% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Real-World Exposure

1 pkg affected

How broadly this vulnerability is actually deployed: weekly install volume shows current usage, and reverse-dependency count shows how many other packages break if it stays unpatched.

277other npm packages depend on this — each one inherits the vulnerability until it's patched upstream

@anthropic-ai/claude-codenpm

13.3Mdownloads / week

Description

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.

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
📦npm	`@anthropic-ai/claude-code`	≥ 0.2.54&&< 2.1.163	2.1.163`npm install @anthropic-ai/claude-code@2.1.163`

Affected Products

1 product · 1 configurations

Application

claude codeanthropic

≥ 0.2.54 && < 2.1.163

range

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update @anthropic-ai/claude-code to 2.1.163 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-54316 is resolved across your whole dependency graph.
Workarounds
Assume what was exposed is already known: rotate any credential, token or key that the affected component could return, restrict the endpoint to callers that genuinely need it, and strip sensitive fields from responses and error output at the boundary rather than relying on the client not to read them.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatModerate

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…

Workaround published by Red Hat

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.

Source: Red Hat security advisory for CVE-2026-54316 (CC BY 4.0)

Frequently Asked Questions

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 s

O3 Security · Impact-Aware SCA

Is CVE-2026-54316 in your dependencies?

Find it across npm, including transitive dependencies.

Scan my dependencies How O3 SCA works

CVE-2026-54316 — @anthropic-ai/claude-code