Data exfiltration via pre-approved WebFetch hostname
Published Jun 23, 2026 · Updated Jun 23, 2026
Information disclosure in Anthropic Claude Code 0.2.54 through 2.1.162 allows attackers to exfiltrate data via WebFetch. A bare-hostname allowlist entry for huggingface.co auto-approves every path, letting injected instructions encode accessible data in requests to attacker-controlled repository files whose server-side download records reveal the values. Exploitation requires untrusted content in the context window and exposes files, environment variables, or command output available to the running agent.
Summary
What happened
Information disclosure in Anthropic Claude Code 0.2.54 through 2.1.162 allows attackers to exfiltrate data via WebFetch. A bare-hostname allowlist entry for huggingface.co auto-approves every path, letting injected instructions encode accessible data in requests to attacker-controlled repository files whose server-side download records reveal the values. Exploitation requires untrusted content in the context window and exposes files, environment variables, or command output available to the running agent.
The record
- CVE
- CVE-2026-54316
- Published
- Jun 23, 2026
- Updated
- Jun 23, 2026
- Vendor
- Anthropic
- Product
- Claude Code
- Classifications
- CWE-515, CWE-200, CWE-183, T1567
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 23, 2026CVE publishedPublication date reported by the CVE source.
- Jun 23, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=>= 0.2.54, < 2.1.163
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo