CVE Watch14 ago 2026

CVE-2026-73555

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/ope

CVSS

5.3

Medio

EPSS

—

KEV

—

Exploit Today

—

0-100

Publicado: 13 ago 2026 · Última mod.: 14 ago 2026 · CWE-209

EPSS · 30d

Sin historial EPSS suficiente todavía.

Descripción técnica

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does not remove traceback-style file paths, allowing unauthenticated malformed JSON requests to /v1/chat/completions, /v1/completions, /tokenize, and /detokenize to disclose the OS username, home and virtual-environment paths, Python version, internal package structure, line numbers, and endpoint handler names. This issue is fixed in version 0.26.0.

Referencias oficiales

CVEs relacionados

CVECVSSEPSSKEVRExplotTítuloVis.

CVE-2026-738443.7 BAJ

—

———CKAN MCP Server is a tool for querying CKAN open data portals. Prior to 0.4.112, error paths reflect raw upstream response bodies and internal exception messages back to the caller instead of a sanitized, generic message. When the server is pointed at (or redirected/SSRF'd to) a host that returns a non-CKAN response, or when an internal exception occurs, the caller receives verbatim upstream content and internal detail (hostnames, internal IPs, DB errors, stack fragments). This vulnerability is fixed in 0.4.112.8h CVE-2026-566204.3 MED

12.0%

——4HCL BigFix Mobile is vulnerable to information disclosure due to improper handling of exceptions and verbose error reporting.4d CVE-2026-436306.5 MED

37.4%

——11llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with an oversized seq_id value to trigger an out-of-bounds read that leaks heap data including pointer values into server logs, defeating ASLR protections and facilitating further exploitation.7d CVE-2026-476225.3 MED

18.3%

——5NVIDIA Dynamo for Linux contains a vulnerability where an attacker could cause the generation of error messages that contain sensitive information. A successful exploit of this vulnerability might lead to information disclosure.7d CVE-2026-69247—

7.3%

——2cryptography is a package designed to expose cryptographic primitives and recipes to Python developers. From 44.0.0 until 50.0.0, pkcs7_decrypt_der, pkcs7_decrypt_pem, and pkcs7_decrypt_smime reported the outcome of decrypting a RecipientInfo's encryptedKey in several distinguishable ways, one of which disclosed the exact length recovered from the RSA operation. The same distinction was also observable by timing. An application that decrypts attacker-supplied EnvelopedData and reflects the outcome gives the attacker a Bleichenbacher oracle against the content-encryption key. Decryption ran as RSA PKCS#1 v1.5 decrypt of encryptedKey, build an AES cipher from the result, then AES-CBC decrypt and PKCS#7 unpad. Invalid RSA padding, a valid padding with a bad key length, a correct length with a wrong key, and the real key each failed or succeeded differently. Case 1 is reachable only where the linked library lacks implicit rejection: OpenSSL 3.0 and 3.1, LibreSSL, and BoringSSL. Exploitation requires a service that auto-decrypts untrusted EnvelopedData matching the victim certificate and answers adaptively at high volume, such as an S/MIME gateway or mail filter. This issue is fixed in 50.0.0.10d CVE-2026-565713.7 BAJ

6.9%

——2HCL iControl was affected by Improper Error Handling vulnerabilities. It involves Out of memory, null pointer exceptions, system call failure, database unavailable, network timeout, and hundreds of other common conditions can cause errors to be generated.9d