Tiago Sequeira (@[email protected]) @_x13

The Skills ecosystem is growing fast , aitmpl.com alone has crossed 1M downloads with hundreds of Skills submitted every month At that scale, automated security scanning on every PR stops being optional. SkillSpector (@NVIDIAAI) does that, static analysis, 64 patterns, risk score 0–100, blocks at 50 Full writeup on how it works and how to integrate it 👇

Daniel San @dani_avila7

2 weeks ago

x.com/i/article/2063…

5 22 138 21K 290

4 9 45 8K 61

View Details

Daniel San @dani_avila7

2 weeks ago

Repo if you want to use it: github.com/nvidia/skillsp…

0 2 8 865 11

View Details

Tiago Sequeira (@[email protected]) @_x13

6 days ago

OWASP Risk Rating Methodology | OWASP Foundation owasp.org/www-community/…

0 0 0 6 0

View Details

Tiago Sequeira (@[email protected]) @_x13

7 days ago

WinLOLBIN-GT: A Behavioural Ground Truth Dataset for ML-Based Detection of Windows LOLBIN Abuse zenodo.org/records/205334…

0 0 0 11 0

View Details

Tiago Sequeira (@[email protected]) @_x13

7 days ago

WinLOLBIN-GT: A Behavioural Ground Truth Dataset for Machine Learning-Based Detection of Windows Living-Off-the-Land Binary Abuse github.com/daniyyell-dev/…

0 0 0 9 0

View Details

cr3ghost @cr3ghost

a week ago

One of the best FREE Windows exploit development and security research blogs out there. Kernel pool exploitation. PTE overwrites. HVCI and kernel CFG bypass. XFG internals. Browser type confusion. Kernel shadow stacks. Secure kernel internals. ARM64 Pointer Authentication bypass. ETW and PPL research. Covers everything from ROP fundamentals all the way to cutting edge ARM64 and VBS security research. Still actively publishing in 2026. connormcgarr.github.io Author: @33y0re #ExploitDevelopment #WindowsInternals #ReverseEngineering

2 105 506 22K 469

View Details

Tiago Sequeira (@[email protected]) @_x13

2 weeks ago

“Threat Hunting Case Study: LOLBins, Registry Staging & Fileless C2 Attack” by Vidhi patel medium.com/@patelvidhi428…

0 0 0 20 0

View Details

Tiago Sequeira (@[email protected]) @_x13

2 weeks ago

github.com/secureagentics…

0 0 0 8 0

View Details

@

2 weeks ago

As an AI Engineer. Please learn: Harness engineering, not just prompt engineering Context engineering, not just long prompts Prompt caching vs. semantic caching tradeoffs KV cache management, eviction, reuse, and memory pressure at scale Prefill vs. decode latency and why they optimize differently Continuous batching, paged attention, and throughput optimization Speculative decoding vs. quantization vs. distillation tradeoffs INT8, INT4, FP8, AWQ, GPTQ, and when quantization hurts quality Structured output failures, schema validation, repair loops, and fallback chains Function calling reliability, tool contracts, argument validation, and idempotency Agent guardrails, loop budgets, tool budgets, and termination conditions Model routing, graceful fallback logic, and degraded-mode UX RAG architecture: chunking, embeddings, hybrid search, reranking, and freshness Retrieval evals: recall, precision, grounding, attribution, and citation quality Evals: golden sets, regression tests, adversarial tests, LLM-as-judge, and human evals LLM observability as a first-class discipline: traces, spans, tokens, latency, errors, and drift Cost attribution per feature, workflow, tenant, and user journey not just per model Safety engineering: prompt injection defense, data leakage prevention, and permission boundaries Multi-tenant isolation, cache safety, and cross-user context contamination prevention Fine-tuning vs. in-context learning vs. RAG vs. distillation and when each is the wrong tool Latency, quality, cost, and reliability tradeoffs across the full inference stack Production failure modes: hallucinated tool calls, malformed JSON, stale retrieval, runaway agents, and silent eval regressions Shipping LLM systems as reliable infrastructure, not demos wrapped around prompts aiengineeringfromscratch.com