Vulnerability · Published Oct 29, 2026 · Assigned by VulnCheck
CVE-2026-119120Crawl4AI 0.9.0 before 0.9.5 Untrusted Model Loading via CosineStrategy model_name
High 7.5
In plain English
A high-severity unsafe deserialization in crawl4ai from unclecode. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 36% of all known vulnerabilities).
Severity (CVSS 3.1)7.5High
Exploit odds (30 days)0.4%top 63.6% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known
Official description
Crawl4AI from 0.9.0 before 0.9.5 fails to filter the CosineStrategy model_name field in untrusted Docker API request bodies, allowing authenticated clients to choose which HuggingFace model the server loads. Attackers can reference a malicious repository with a pickle weight file to execute Python code under PyTorch below 2.6, or exhaust disk and memory.
Affected products (as reported)
Weakness: CWE-502 · Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
References
- GitHub Security Advisory (GHSA-f856-7xp9-w3cc) vendor-advisory
- VulnCheck Advisory: Crawl4AI 0.9.0 before 0.9.5 Untrusted Model Loading via CosineStrategy model_name third-party-advisory