Anthropic: community verdicts

1 notable / known-exploited Anthropic CVE the community has triaged.

ⓘ Not an exhaustive list: we focus on the findings that matter (exploited / notable). For every Anthropic CVE, see NVD ↗.

Exploitation first, with newly exploited CVEs rising above old ones

CVE-2026-54316CRIT 9.1Real · low riskEPSS 0%
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.