UNST33R

#agent-security

5 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.

· updated October 27, 2026

Triage 5,000 bulk vulnerability reports for about $50

Anthropic's OSS Scanner sends maintainers thousands of unvalidated model-generated findings. A reproducible triage workflow with cve.now MCP and unst33r-deepseek: normalization, dedup, reachability pre-screen, and a human queue, with per-report cost math.

· updated October 27, 2026

Why multi-agent harnesses fail differently: an attack-surface primer

Single-agent red-team methods lose fidelity against multi-agent systems. The structural reasons, a per-hop testing method, hop telemetry schemas, and a cost model that keeps wide harnesses affordable.

· updated October 26, 2026

Automated CVE triage and PoC verification with cve.now MCP and unst33r-deepseek

Connect the free cve.now MCP vulnerability feed to an OpenClaw or Hermes security agent backed by unst33r-deepseek to check lockfiles, trace reachable sinks, draft regression PoCs, and budget continuous CVE verification without mid-run refusals.

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.