CVE-2026-54316: anthropic claude_code Permissive List of Allowed Inputs
Vulnerability summary
CVE-2026-54316 is a critical (CVSS 9.1) Permissive List of Allowed Inputs vulnerability in anthropic claude_code. EPSS estimates a 0.52% chance of exploitation in the next 30 days, higher than 43.2% of scored vulnerabilities.
Timeline
- 23-06-2026PublishedVulnerability first disclosed.
- 23-06-2026Last modifiedVulnerability information updated.
Description
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.
CVSS metrics
5 scores · 3 sources · 2 versions- OSV · NpmEcosystem advisory · calculated6.0MediumCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
- NVDNIST6.0MediumCVSS: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:X
- OSV · NpmEcosystem advisory · calculated9.1CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
EPSS trend
Probability
0.52%
Chance of exploitation in the next 30 days
Percentile
43%
Versus all other CVEs
30-day change
0.00 pp
From 0.52% on 21-09-2026
Known exploited
Compare KEV catalogsNot in any of the 3 tracked catalogs.
Public exploits
0 foundNo public exploits indexed.
Weaknesses
CWE · root cause- CWE-183Permissive List of Allowed InputsThe product implements a protection mechanism that relies on a list of inputs (or properties of inputs) that are explicitly allowed by policy because the inputs are assumed to be safe, but the list is too permissive - that is, it allows an input that is unsafe, leading to resultant weaknesses.
- CWE-200Exposure of Sensitive Information to an Unauthorized ActorThe product exposes sensitive information to an actor that is not explicitly authorized to have access to that information.
- CWE-515Covert Storage ChannelA covert storage channel transfers information through the setting of bits by one program and the reading of those bits by another. What distinguishes this case from that of ordinary operation is that the bits are used to convey encoded information.
Affected systems
@anthropic-ai1 product
- claude-code≥ 0.2.54, < 2.1.163
Anthropic1 product
- claude_code≥ 0.2.54, < 2.1.163
Anthropics1 product
- claude-code≥ 0.2.54, < 2.1.163
3 vendors · 3 products
References
3 links- github.com/anthropics/claude-code/security/advisories/GHSA-fg94-h982-f3mmX Refsource CONFIRMWEBThird Party Advisory