All articles
DEEP DIVE · 8 min read

What AI Actually Finds: LLM-Assisted Work Across Pentest, SOC and Malware

I've folded LLMs into day-to-day security work for a while now. This is an honest account of what they find, where they save hours, and where they hand you a confident wrong answer that costs you more than they saved.

Share

Offense: pattern-spotting at scale

The model is strong at the boring, high-volume review that humans skim.

  • Reads a whole handler set and flags the one route missing an authorization check
  • Spots IDOR / BOLA shapes across dozens of endpoints faster than manual diffing
  • Generates payload and mutation lists, regexes, and one-off parser scripts
  • Weak at business logic and multi-step chains — it needs you to frame the abuse case

SOC: detection-as-code and triage

This is where it pays off most. It drafts Splunk SPL and Sigma rules from a plain-English description, summarizes noisy alert clusters into a timeline, and explains an unfamiliar Windows event ID in context. You still review every rule — it will invent a field name that doesn't exist in your data model.

EDR and malware: deobfuscation and first-pass triage

Feed it an obfuscated PowerShell or JScript loader and it will unwind the string-building and base64 layers in minutes, name the likely technique, and draft a YARA rule from the decoded artifacts. Treat the YARA rule as a starting point and test it for false positives before it ships.

Where it fails — plan for this

Hallucinated CVE numbers, exploit code that looks right and isn't, missed context because it never saw the running system, and total confidence while being wrong. Every AI-surfaced finding gets manually reproduced before it enters a report.

⟩ sample findings — sanitized

What this kind of project turns up

Representative findings from real engagements. Details are altered and unlinked from any client — the pattern and severity are what matter.

SKR-AI-01Missing authorization check surfaced by AI code review
High

The model flagged one REST handler in a set of ~40 that trusted a client-supplied user ID with no ownership check. Manual review had skimmed past it. Reproduced and confirmed as BOLA.

SKR-AI-02AI-drafted SPL caught a scheduled-task persistence pattern
Medium

A plain-English prompt produced an SPL query for `schtasks`/`at` creation with unusual parent processes; it fired on activity analysts had previously filtered as noise.

SKR-AI-03PowerShell loader deobfuscated in minutes
Medium

Multi-layer base64 + char-code obfuscation unwound by the model; decoded C2 domain and mutex became IOCs and a YARA rule.

SKR-AI-04AI false positive — 'SQL injection' in a parameterized query
Low

Model flagged a string-concatenated log line as SQLi; the query was actually parameterized. Included here as the failure mode: always verify.

Tools mentioned

ClaudeGitHub CopilotSplunk AI AssistantcapaYARAPyRITSigma
⟩ takeaway

AI is a force multiplier for review-at-scale, SPL and Sigma drafting, and malware deobfuscation — not a scanner. It finds real issues a tired human misses, and invents issues a tired human might believe. Reproduce everything.

⟩ keep reading

Related articles

Let's Connect

connect

For VAPT engagements, SOC consulting, AI/LLM security assessments, cloud reviews, incident response retainers or training collaborations — let's build a defensible stack together.

Available worldwide · Remote & on-site