Vulnerability in @anthropic-ai/claude-code (CVE-2026-54316)
Summary
Vulnerability in @anthropic-ai/claude-code (CVE-2026-54316). Confidential information can be exposed externally. Mitigation: upgrade to 2.1.163 or later.
Original description
The description as published by the source.
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.
Source: GitHub Security Advisories (Global) NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-54316 has been found in @anthropic-ai/claude-code.
Confidential information can be exposed externally. CVSS score: 9.1/10.
What to do: upgrade @anthropic-ai/claude-code to 2.1.163 or later.
If unsure, ask your IT team or search "@anthropic-ai/claude-code CVE-2026-54316" on the vendor's site.
CVE-2026-54316 (@anthropic-ai/claude-code) — CWE-183 / CVSS v3 9.1
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Patched: 2.1.163 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-183) exists in @anthropic-ai/claude-code.
Check the vendor advisory for the affected versions of @anthropic-ai/claude-code.
Severity: Critical (CVSS 9.1/10). Confidential information can be exposed externally.
Update to 2.1.163.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r '@anthropic-ai/claude-code' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r '@anthropic-ai/claude-code' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
@anthropic-ai/claude-codeを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade @anthropic-ai/claude-code to 2.1.163ステージング環境で 2.1.163 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory nvd.nist.gov
- package github.com
- web github.com
- web github.com