CVE-2026-115915High· 8.1▾ TwilightvLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 44.6 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Oct 27.
Disclosure to exploitation, from the record and what we observed since indexing it.
0.6%
Disclosed via OSV
Last analysed / modified upstream
0.6% → 0.7%
In vLLM 0.30.0, ImageMediaIO passes attacker-controlled image bytes to Pillow's format autodetection without restricting the accepted formats; the request's MIME label does not constrain decoder selection. An EPS payload labeled image/png reached the host's Ghostscript executable. On a host with Ghostscript affected by CVE-2024-29510, this exposes the known Ghostscript sandbox escape through vLLM's image-loading path and can execute commands with the vLLM process's privileges. A bounded marker-command payload executed through the PyPI wheel's actual ImageMediaIO.load_base64() implementation using Debian Ghostscript 10.03.0. The loader-level execution is reproduced; the HTTP request path is source-traced but was not exercised end to end. This report concerns vLLM's untrusted-format dispatch and does not claim a new Ghostscript vulnerability. Exploitation requires an image-capable request path, a caller able to reach it under the deployment's authentication policy, and a vulnerable host Ghostscript build.
ImageMediaIO is the boundary where attacker-controlled bytes enter Pillow's format autodetection: the declared MIME type does not constrain decoder selection, and the loader calls Image.open(BytesIO(data)) without a Pillow format allowlist. Pillow recognizes EPS by its file signature, and vLLM's subsequent image.load() call enters Pillow's EPS processing path. The OpenAI chat multimodal parser reaches this path through parse_image() and fetch_image() and the media connector; the data URL path extracts the MIME label and forwards the bytes to the loader (source). This is the vLLM-specific issue: untrusted image bytes can select a Pillow-supported format parser. Each downstream impact depends on the relevant parser, component version, and host configuration.
Pillow recognizes EPS by its file signature and invokes Ghostscript with -dSAFER, -sDEVICE=pnmraw, and the untrusted EPS input (Pillow EPS plugin, load path). The command execution in this report uses the already-known Ghostscript CVE-2024-29510, which allows crafted PostScript to bypass -dSAFER; Ghostscript lists 10.03.1 as the upstream fixed version (Ghostscript CVE details). This is an N-day dependency chain: CVE-2024-29510 provides the command-execution primitive, while the vLLM-specific issue is that untrusted, remotely supplied image bytes can reach the affected interpreter. No new Ghostscript flaw is claimed here.
The vLLM Python requirements declare Pillow but not Ghostscript, so this execution chain depends on a Ghostscript executable supplied by the host or deployment image. I reproduced command execution with the PyPI vllm==0.30.0 wheel, Pillow 12.3.0, and Debian amd64 Ghostscript 10.03.0~dfsg-1. The Codean Labs CVE-2024-29510 testkit identified that Ghostscript build as vulnerable. The adapted EPS payload ran only touch on a temporary marker. The marker existed after the loader call, although Pillow then raised ValueError because the exploit changes Ghostscript's output device. The API route was traced in source but a model-backed HTTP request was not run. Only PyPI vllm==0.30.0 was checked; no wider affected release range or other Ghostscript vendor build is claimed.
The same input boundary also exposes a separate Pillow-only denial-of-service condition when the installed Pillow version is 12.0.0–12.2.0. CVE-2026-59203 is triggered by a negative %%BeginBinary byte count and causes Pillow's EPS parser to loop during Image.open(); it does not invoke Ghostscript or provide code execution (Pillow advisory). The published vllm==0.30.0 requirements leave Pillow unpinned, so an existing environment can retain an affected Pillow version; the source at commit bc21cba9673cfc2256a2726b4bc32f062237cd35 requires pillow>=12.3.0. In an isolated local check with Pillow 12.2.0, the official sample hung through ImageMediaIO.load_bytes() and MediaConnector.fetch_image_async(). Eight concurrent image loads occupied the connector's eight media-loading threads and left a benign image load queued. Pillow 12.3.0 rejected the sample promptly. This confirms a conditional media-processing DoS path, separate from the Ghostscript RCE chain; full HTTP-server availability was not measured.
When a vLLM image-processing endpoint accepts attacker-supplied content and the host has Ghostscript affected by CVE-2024-29510, a caller who can reach the endpoint can trigger command execution as the vLLM process user. API-key authentication and network access controls determine who can reach the request path. Deployments without Ghostscript or with a build fixed for CVE-2024-29510 are not affected by this execution chain. Separately, existing environments that run vLLM 0.30.0 with Pillow 12.0.0–12.2.0 are exposed to CVE-2026-59203 through the same image-format dispatch boundary; the demonstrated impact is exhaustion of media-loading workers, and this Pillow CVE does not cause RCE. The report asks vLLM to assess and address the unsafe dispatch of untrusted image bytes and the affected dependency combinations.
This advisory was fixed in MR60022.
vllm < 0.32.0Upgrade to a patched release:
vllm 0.32.0Connected by shared product, vendor, weakness, or advisory.
CVE-2026-115911Medium· 6.5vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
CVE-2026-115912High· 7.5vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
CVE-2026-115913Medium· 6.5vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
CVE-2026-115916Medium· 6.5vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
CVE-2026-115917Low· 3.4vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server
CVE-2026-115914Medium· 6.5vLLM DeepSeek-OCR image processing vulnerable to denial of service