UNST33R

#security-event

8 posts

#security-event (8)#abliteration (7)#red-teaming (6)#vulnerability-analysis (6)#open-models (5)#tutorial (5)#model-selection (5)#agent-security (5)#tools (4)#supply-chain (3)#php (2)#ransomware (1)#llm-infra (1)#ai-agents (1)#ai-red-teaming (1)#disclosure-policy (1)#triage (1)#attack-surface (1)#data-report (1)#threat-intel (1)#inference (1)#llama.cpp (1)#policy (1)#open-weights (1)#rce (1)#announcement (1)#deepseek (1)#benchmarks (1)#tiers (1)#model-safety (1)#primer (1)

Operation n0n: what the first criminal use of abliterated models actually shows

SOCRadar's STRU unit documented an exposed n0n ransomware workspace where an opencode agent ran uncensored and abliterated models across 154 model entries. The full breakdown: $7,216 in LLM spend, zero CVEs, credential-only access, and what it changes for authorized red-team work.

The abliterated takedown wave: what disappeared from Hugging Face, why, and what users are doing about it

MiMo-UNCENSORED, penclaw-GLM-abliterated, huihui Kimi abliterated GGUFs and more vanished from Hugging Face in October 2026. A fact-checked breakdown of the removals, the backup movement, and the supply-side outlook.

llama.cpp CVE-2026-116096: the mmproj file is part of your attack surface

An out-of-bounds write in llama.cpp's Pocket-TTS component, triggered by a malicious mmproj file, with a public exploit. Timeline, auxiliary-file attack surface table, local verification script, and what red-team operators should check.

· updated October 27, 2026

Anthropic's OSS Scanner and Bitcoin Core's dilemma: AI vulnerability discovery just got institutional

Anthropic will scan open-source projects with its strongest models for free: 29,000 candidate findings in six months, 88% validation on criticals. Bitcoin Core is debating joining, and its year-long embargo policy is the sticking point. What this shift means for red-team operators.

PHP2Shell day 3: the exploitation curve, the embargo leak, and a second supply-chain shock

Cloudflare's numbers show exploitation starting before disclosure. WatchTowr confirms live attempts. Plus the eMudhra CA key fiasco in the same 48-hour window. What ops and red teams should do now.

LiteLLM 1.107.0 backdoor: attack analysis and a self-audit checklist

A malicious LiteLLM 1.107.0 release on PyPI and Docker shipped a credential stealer with dormant C2, built from stolen GitHub OAuth tokens. What the payload does, how to check your fleet, and why the code reads like LLM output.

PHP2Shell: pre-auth RCE in core PHP, found by AI agents

CVE-2026-109618 and CVE-2026-109619 let unauthenticated attackers execute code on stock PHP 8.2 through 8.5, before any application code runs. Patch matrix, interim mitigations, and how to run the same AI-assisted patch triage Wiz used.

From prompt injection to RCE: Testing agents against recent LangChain, MCP, and Semantic Kernel CVEs

How recent CVEs in LangChain, Model Context Protocol (MCP), and Semantic Kernel turn prompt injection into remote code execution, and how to test your own agents with Promptfoo, PyRIT, and Garak using UNST33R attacker models.