187 matches found
EUVD-2026-114513
In Trail of Bits fickling through 0.1.12, the processimport method in fickle.py adds an imported name to the likelysafeimports set whenever the source module is present in sys.stdlibmodulenames and the name is absent from the UNSAFEIMPORTS denylist, without inspecting what the name resolves to or...
CVE-2026-16760
In Trail of Bits fickling through 0.1.12, the processimport method in fickle.py adds an imported name to the likelysafeimports set whenever the source module is present in sys.stdlibmodulenames and the name is absent from the UNSAFEIMPORTS denylist, without inspecting what the name resolves to or...
CVE-2026-16760 Fickling check_safety() bypass: likely_safe_imports grants module-origin trust to unvalidated standard library callables
In Trail of Bits fickling through 0.1.12, the processimport method in fickle.py adds an imported name to the likelysafeimports set whenever the source module is present in sys.stdlibmodulenames and the name is absent from the UNSAFEIMPORTS denylist, without inspecting what the name resolves to or...
CVE-2026-16760 Fickling check_safety() bypass: likely_safe_imports grants module-origin trust to unvalidated standard library callables
In Trail of Bits fickling through 0.1.12, the processimport method in fickle.py adds an imported name to the likelysafeimports set whenever the source module is present in sys.stdlibmodulenames and the name is absent from the UNSAFEIMPORTS denylist, without inspecting what the name resolves to or...
CVE-2026-16760
The Trail of Bits fickling tool (through version 0.1.12 ) contains a security bypass in the check_safety() function. The _process_import() method in fickle.py incorrectly grants module-level trust to any name from sys.stdlib_module_names not in the UNSAFE_IMPORTS denylist. Because the OvertlyBadE...
CVE-2026-16760: trailofbits fickling: In Trail of Bits fickling through 0.1.12, the _process_import() method in fickle.py adds an imported name to the…
In Trail of Bits fickling through 0.1.12, the processimport method in fickle.py adds an imported name to the likelysafeimports set whenever the source module is present in sys.stdlibmodulenames and the name is absent from the UNSAFEIMPORTS denylist, without inspecting what the name resolves to or...
VLLM: Public Multimodal SHM Handle Forgery Reaches Worker-side `pickle.loads()` With Insecure Serialization Disabled
Affected - Ecosystem / package: pip / "vllm" - Affected versions: vLLM 0.32.0. Summary When "--mm-processor-cache-type shm" is enabled, vLLM's multimodal SHM cache represents a cached item with an "address" and "monotonicid" pair and treats that pair as authority to dereference shared memory in...
EUVD-2026-110022
vLLM: Public multimodal SHM handle forgery reaches worker-side pickle.loads with insecure serialization disabled...
vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM 0.32.0. Summary When --mm-processor-cache-type shm is enabled, vLLM's multimodal SHM cache represents a cached item with an address and monotonicid pair and treats that pair as authority to dereference shared memory in the worke...
GHSA-6757-HGGM-HP2W vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM 0.32.0. Summary When --mm-processor-cache-type shm is enabled, vLLM's multimodal SHM cache represents a cached item with an address and monotonicid pair and treats that pair as authority to dereference shared memory in the worke...
PYSEC-2026-4345
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...
PYSEC-2026-4345
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...
CVE-2026-115912
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...
CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...
CVE-2026-115912
In versions prior to 0.32.0 , the vLLM inference and serving engine for large language models is vulnerable to arbitrary Python execution. An authenticated caller can exploit this by placing forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-o...
CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...
CVE-2026-115912
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...
PT-2026-123435
Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.32.0 Description An authenticated caller can provide forged shared-memory address and monotonic id values within the public multimodal features.kwargs data. In scale-out deployments where shared-memory multimodal cachi...
WS-2026-0140
vllm 0.20.0 - 0.31.0: the public /inference/v1/generate route accepts caller-forged multimodal SHM cache handles address, monotonicid that the worker dereferences without authentication, reaching pickle.loads on attacker-staged bytes when the SHM multimodal processor cache is enabled...