CVE-2026-0599 is a high-severity (CVSS 7.5) Uncontrolled Resource Consumption vulnerability in text-generation. EPSS puts its 30-day exploitation probability at 27.6% (98th percentile). A fix is available for text-generation — see the affected versions and patch details below.
Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference
Exploitation Status
Proof-of-concept exploit code exists
- CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
- CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
Exploitation and automatability from CISA’s SSVC triage for CVE-2026-0599.
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
How urgent is this, really
CVE-2026-0599 plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.
Where this sits among everything scored
Of 376,715 CVEs with a current EPSS score, this one falls in the 10–50% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.
Real-World Exposure
text-generationReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.
Description
A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | text-generation | all versions | 3.3.7pip install --upgrade 'text-generation==3.3.7' |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for text-generation, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update text-generation to 3.3.7 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-0599 is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like CVE-2026-0599 can be triaged on real exposure rather than presence alone.
Tailored to CVE-2026-0599. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is CVE-2026-0599 in your dependencies?
O3 Security finds CVE-2026-0599 across PyPI dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.