CVE-2026-54316
Info Disclosure in Anthropic Claude Code 0.2.54 – 2.1.163
Raw vector
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-54316 is a medium-severity Permissive List of Allowed Inputs (CWE-183) vulnerability in Anthropic Claude Code. Its CVSS base score is 6.0 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Token Impersonation/Theft (T1134.001); ranked at the 43th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations.
The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and AC-4 (Information Flow Enforcement) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-38538
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- N/A
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: claude, huggingface, claude, huggingface, claude, claude
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
- 6 hardening rules · 5 OS baselines
V1.5.2V4.4.2V10.4.9V11.7.1
Mitigating Controls (NIST 800-53 r5) AI
Access enforcement directly stops unauthorized actors from obtaining sensitive information.
Information flow enforcement structurally prevents sensitive data from reaching unauthorized recipients.
Protection of information at rest prevents unauthorized exposure of stored sensitive data.
Transmission confidentiality mechanisms stop exposure of sensitive data on the wire.
Least privilege reduces the set of actors who can reach sensitive information.
SC-31 performs analysis specifically to identify potential covert channels in system communications.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.AA-05 directly enforces least-privilege authorization that blocks most unauthorized disclosures, yet CWE-200 also arises from logging, error messages, and side-channel paths that access controls alone do not address.
PR.DS-10 mostly prevents CWE-200 by directly eliminating unauthorized access to sensitive data-in-use, yet only partially addresses the weakness because CWE-200 spans many other exposure vectors outside runtime protection.
PR.IR-01's segmentation/zero-trust controls largely eliminate network-level unauthorized access paths that enable exposure, yet CWE-200 spans many additional vectors (API responses, logs, app logic) that network controls alone cannot close.
Secure SDLC practices catch most exposure flaws via design, testing and release controls, yet CWE-200 spans runtime/config issues a single development outcome cannot fully close.
Runtime and data monitoring can surface anomalous shared-resource bit patterns that indicate covert storage.
PR.AA-01 supplies proper credential lifecycle controls that reduce unauthorized access paths, yet leaves many other exposure vectors (error messages, logging, side channels, etc.) unaddressed.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Clear rules on handling copies, storage, and disposal of classified information lower the likelihood that sensitive data will be left accessible to unauthorized actors.
Requiring the return of all physical and electronic assets plus secure deletion of organizational data from personal devices reduces the chance that sensitive information remains accessible to departing personnel.
By requiring owners to assign sensitivity labels and corresponding handling rules, the control ensures that information is not left unmarked and therefore reduces the chance that sensitive data will be exposed to unauthorized actors.
By requiring classification labels and metadata on all information assets, the control makes it harder for sensitive data to be inadvertently exposed because downstream systems and users can recognize and enforce handling rules based on those labels.
Requiring encryption, access controls, and recipient authentication for transfers directly reduces the chance that sensitive data reaches an unauthorized observer.
Secure delivery, protected storage, and confidentiality of allocation records limit exposure of authentication material to unauthorized observers.
Hardening callouts derived
Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (higher-evidence rows only; rows rated `none` are excluded).
Ubuntu 22.04 (1 rule)
- V-260470 Ubuntu 22.04 LTS, when booted, must require authentication upon booting into single-user and maintenance modes. prevents CWE-200
Ubuntu 24.04 (2 rules)
- V-270647 Ubuntu 24.04 LTS must not have the telnet package installed. prevents CWE-200
- V-270675 Ubuntu 24.04 LTS when booted must require authentication upon booting into single-user and maintenance modes. prevents CWE-200
Windows 10 (1 rule)
- V-220737 Administrative accounts must not be used with applications that access the Internet, such as web browsers, or with potential Internet sources, such as email. prevents CWE-200
Windows Server 2016 (1 rule)
- V-224974 Domain-created Active Directory Organizational Unit (OU) objects must have proper access control permissions. prevents CWE-200
Windows Server 2019 (1 rule)
- V-205743 Windows Server 2019 organization created Active Directory Organizational Unit (OU) objects must have proper access control permissions. prevents CWE-200