Security Digest · Vulnerability record
CVE-2026-54316: Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch
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…
CVSS 6.0 Medium EPSS 0.5% · p43 Check exposure
Should you act?
Normal patch cycle
No exploitation signal; fix it in your next routine update if you are affected. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 0.5%, percentile 43: FIRST’s model estimates a 0.5% chance of exploitation activity in the next 30 days, higher than 43% of all scored CVEs (low). EPSS is a probability, not a verdict.
- Editorial verdict: Check exposure. Gemini CLI and Claude Code Flaws Expose CI Secrets — If an AI coding agent runs in your CI on content outsiders can write (issues, PRs, comments), check versions and workflow permissions this week; laptop users on auto-update already have the fixes.
What it is
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.
Weakness type: CWE-183, CWE-200, CWE-515.
Product: anthropics claude-code · Assigned by: GitHub_M · Published: 2026-06-23
Affected and fixed versions
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| anthropics | claude-code | >= 0.2.54, < 2.1.163 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_M | 4.0 | 6 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 |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Attack requirements: present (depends on deployment conditions)
- Privileges required: none (no login)
- User interaction: passive
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none, automatable no, technical impact partial.
- FIRST EPSS (model of 2026-10-21): 0.52% probability of exploitation activity in the next 30 days; percentile 43.
Timeline
- — CVE record last updated
- — CVE record published by GitHub_M
- — erroneo.us brief: Gemini CLI and Claude Code Flaws Expose CI Secrets
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- CVE.org record CVE-2026-54316 cve.org
- NVD entry CVE-2026-54316 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com