Path Traversal in Anthropic Claude Code
CVE-2025-54794
Claude Code is an agentic coding tool. In versions below 0.2.111, a path validation flaw using prefix matching instead of canonical path comparison, makes it possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of (or ability to create) a directory with the same prefix as the CWD and the ability to add untrusted content into a Claude Code context window. This is fixed in version 0.2.111.
Vulnerability class: Path Traversal (Directory Traversal)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.1 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N.
EPSS exploit prediction
EPSS 0.015, 73.8th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Anthropic Claude Code
- Anthropics Claude-Code — versions < 0.2.111
Weakness classification (CWE)
Public exploits and proof-of-concept code
1 public repository with exploit or proof-of-concept code for this CVE:
- AdityaBhatt3010/CVE-2025-54794-Hijacking-Claude-AI-with-a-Prompt-Injection-The-Jailbreak-That-Talked-Back (40 stars, last pushed 2025-08-06): A high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of code.
Also mentioned in 7 other repositories (ARPSyndicate/cve-scores, asakaguchi/blocks-slack-orchestrator, asakaguchi/cc-safe-stack, …). These reference the CVE in a list, notes or a scanner and are not exploit code for it.
References
This CVE has public exploit evidence. See the latest CVEs with public exploits.