Covert Storage Channel

A 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.

CVEs (1)

CVE VENDORS PRODUCTS UPDATED PUBLISHED CVSS
CVE-2026-54316 1Anthropic 1Claude Code Jun 29, 2026 Jun 23, 2026 6.0 MEDIUM· v4 9.1 CRITICAL· v3 N/A· v2 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 mode...Show more 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.Show less

CVE

VENDORS

PRODUCTS

UPDATED

PUBLISHED

CVSS

CVE-2026-54316

1Anthropic

1Claude Code

Jun 29, 2026

Jun 23, 2026

6.0 MEDIUM· v4

9.1 CRITICAL· v3

N/A· v2

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.Show less