Nixpkgs security tracker

Untriaged

Permalink CVE-2026-71486

4.3 MEDIUM

CVSS version (CVSS): 3.1
Attack Vector (AV): Network (N)
Attack Complexity (AC): Low (L)
Privileges Required (PR): Low (L)
User Interaction (UI): None (N)
Scope (S): Unchanged (U)
Confidentiality (C): None (N)
Integrity (I): None (N)
Availability (A): Low (L)
Modified Attack Vector (MAV): Network (N)
Modified Attack Complexity (MAC): Low (L)
Modified Privileges Required (MPR): Low (L)
Modified User Interaction (MUI): None (N)
Modified Confidentiality (MC): None (N)
Modified Scope (MS): Unchanged (U)
Modified Integrity (MI): None (N)
Modified Availability (MA): Low (L)

created 6 days, 17 hours ago Activity log

Created suggestion 6 days, 17 hours ago

vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.