Skip to content
VC
Service · Signature offering

Defensive diagnostic of AI systems and infrastructure in production

I attack your LLM agents, RAG, MCP servers and infrastructure per OWASP LLM Top 10 — finding what classic pentesters miss.

01
AI-specific, not classic

Prompt injection, RAG poisoning, MCP tool poisoning, token bomb — vectors that aren't in Burp / Nessus

02
Production-grade lens

I run 10+ AI systems in production myself. Was a media-buyer with a $1.34M ad budget — saw the performance stack from the inside

03
FZ-152 / KII compliance

Up to 20M ₽ + 3% of revenue in fines for PII leaks. From Jan 1, 2026187-FZ KII blocks foreign software in banks / oil & gas / government

01 · Pricing

Three formats — from entry diagnostic to an ongoing retainer

Express to understand 'how bad is it', Full Audit for serious risks and compliance, retainer — because AI security changes every 4–6 weeks.

Tier 1

Express Security Diagnostic

25,000 ₽
1 business day

Quick entry check: shortened checklist, one live attack, PDF with top-5 risks. Psychological filter before a full audit.

  • 60-min discovery call: architecture, LLM/API, where PII lives
  • 6-hour check against a shortened checklist
  • Live demo of one attack (prompt injection or DNS/SSL/.env exposure)
  • PDF 4–6 pages: top-5 to fix first, severity, commands/code
  • 30-min debrief on the results
Book the diagnostic

~3-4 out of 10 upgrade to Full Audit

Most chosen
Tier 2

Full Security Audit

from 200,000 ₽
2–3 weeks

Full red-team cycle across 4 domains: AI/LLM, infrastructure, FZ-152, business logic. 30–50 page report + live demo + 30 days Q&A.

  • Full red-team cycle per OWASP LLM Top 10 (2025)
  • 4 domains: AI/LLM 40% · Infra 25% · Data Privacy 20% · Business Logic 15%
  • Final report 30–50 pages with evidence and compliance mapping
  • Live demo of 1–2 highest-impact vectors on your environment
  • 90-min readout session + 30 days Q&A on fixes
Discuss the full audit

200–600k ₽ range depending on scope and number of AI agents

Tier 3

Continuous Security Engagement

from 40,000 ₽/mo
retainer, min 6 mo

AI security changes every 4–6 weeks. The retainer keeps your AI infrastructure in an up-to-date threat model between releases.

  • Basic 40k: monthly re-scan, CVE alerts in Telegram, 2h Q&A
  • Basic +: quarterly report on risk dynamics
  • Pro 100k: + pre-release review of every AI feature (2/mo)
  • Pro +: embedded 1 day/week in your team
  • Pro +: threat-intel briefing, 24h SLA on critical issues
Discuss the retainer

80% of clients move to a retainer after the Full Audit

02 · Methodology

19 check points across 4 domains

The checklist is built around risk, not 'easy to check'. OWASP LLM Top 10 (2025) is the foundation of the AI domain, classic infrastructure is the base, FZ-152 / 187-FZ is mandatory regulatory for RU legal entities, sector-specific is what we see in real ad accounts and e-com setups.

Domain A

AI/LLM Security

OWASP LLM Top 10 (2025) — 8 checks

Weight in Tier 2 40%
A1 Critical

Direct prompt injection

Jailbreaks via role-play, multi-turn escalation, encoded payloads: base64 / unicode / ROT13

A2 Critical

Indirect prompt injection (RAG / docs / webhooks)

Attack via data the model itself loads.

Ref: EchoLeak CVE-2025-32711, CVSS 9.3

A3 High

System Prompt Leakage (LLM07:2025)

Extraction of system prompt with embedded keys or internal-API URLs

A4 Critical

Excessive Agency (LLM06:2025)

An agent with write access does what it shouldn't.

Ref: CVE-2025-53773 GitHub Copilot RCE, CVSS 9.6

A5 High

Unbounded Consumption / Cost-overflow (LLM10:2025)

Token bomb: $10k/mo burned with no cap. The attacker generates traffic until you go bankrupt.

A6 Critical

MCP Server / Tool Poisoning

Attack via a third-party MCP server. Including the well-known 'thank you' issue.

Ref: CVE-2025-54136 · Claude Code CVE-2025-59536 · CVE-2026-21852 (Check Point Research)

A7 Medium

Vector / Embedding Weaknesses (LLM08:2025)

Embedding inversion, membership inference, RAG poisoning via substituted documents in the vector DB

A8 High

Sensitive Information Disclosure (LLM02:2025) + PII in logs

PII leak via model responses, log aggregators, error tracking. Synthetic client with realistic PII for verification

Domain B

Infrastructure

6 checks for perimeter and dependencies

Weight in Tier 2 25%
B9 Medium

DNS / Email hygiene

SPF, DKIM, DMARC (often `p=none` — open invoice spoofing), CAA, DNSSEC

B10 Medium

SSL / TLS configuration

SSL Labs target A+, HSTS preload, correct cipher suites, OCSP stapling

B11 High

WAF / CDN review

Bypass via encoded payload, origin IP leak through DNS history / SSL cert / mail headers

B12 Critical

Secrets management surface

`gitleaks` over history, API keys in client-side JS bundle, `.git/` exposed, .env in backup folders

B13 High

Dependency CVE scan

npm / pip / go.mod / Cargo.lock against an up-to-date CVE database.

Ref: Shai-Hulud npm malware · Sonatype 454k+ malicious packages 2026

B14 High

Backup + DR test

Actually restore from backup on staging. 60% of companies have a backup, ~30% can actually restore

Domain C

Data Privacy / RU Regulatory

FZ-152 / 187-FZ KII / PII redaction

Weight in Tier 2 20%
C15 Critical

FZ-152 compliance

Geo storage (PII of Russian citizens on RU territory), sub-processors, RKN registry. 2026 fines: up to 20M ₽ + 3% of revenue. 6–18M ₽ for failing to report a breach in 24/72h

C16 Critical

187-FZ KII readiness

From Jan 1, 2026 foreign software is prohibited in banks, oil & gas, telecom, government sector. Cursor / Claude / OpenAI = formal violation. Alternatives: GigaChat on-prem, YandexGPT, Continue.dev. Fine up to 500k ₽ + blocking

C17 High

PII redaction in LLM prompts

Synthetic client with realistic PII, dump every prompt on the way to OpenAI / Anthropic. Verify regex filters against missed names, INN, phone, email, passport

Domain D

Business Logic / Sector

Authentication and vertical-specific

Weight in Tier 2 15%
D18 High

Auth & session

Token storage (httpOnly vs localStorage), rotation, IDOR, webhook HMAC, replay protection, race conditions in payment flow

D19 Medium

Media-buying / e-com specific

Cloaker probe, Keitaro fraud detection, pixel firing, CAPI integration with HMAC, IP-blocklist hygiene, fingerprint leak via third-party tags

03 · What we usually find

Stats from real audits

Distribution of findings by severity. Critical in ~30% of companies is not a sales scare story — it's the average baseline of the 2025–2026 AI deployment market.

Critical
~30% of audits
  • OpenAI / Anthropic API key in the client-side bundle — 30 sec to extract, $50k overnight
  • Indirect prompt injection enables data exfiltration (EchoLeak pattern)
  • System prompt contains embedded keys or internal-API URLs
High
~60% of audits
  • PII sent to OpenAI without anonymization — up to 20M ₽ + 3% of revenue
  • MCP server tool poisoning via invisible instructions in description
  • No rate-limit on the LLM endpoint — token-bomb DoS
Medium
~80% of audits
  • DMARC in `p=none` mode — invoice spoofing from the company's address
  • SSL Labs grade B/C, no HSTS preload
  • Backup not tested for > 12 months
  • Dependencies CVE older than 90 days, webhook without a signature
Low
~95% of audits
  • CSP headers missing, exposed `.git/config`
  • HSTS preload missing, verbose error messages
  • X-Frame-Options not set, open referrer policy
04 · What's in the final report

Tier 2 deliverable — 30–50 pages with evidence and roadmap

The report is written to be readable both by a CEO and by the engineer who will fix it. Every finding comes with reproducible evidence and a specific command / code fix.

01
1 page

Executive summary

For CEO / CTO / board: risk overview, business impact, fix budget

02
2 pages

Methodology

OWASP LLM Top 10 / 187-FZ / FZ-152 / CVE references — what was checked and why

03
15–30 pages

Findings list

Each item: ID, severity, evidence (screenshot / curl command), impact, fix recommendation, verification method

04
2 pages

Prioritized roadmap

Now / Next / Later — what to fix in the first 48 hours, in the first month, in the quarter

05
variable

Appendix

Full logs, compliance mapping (FZ-152 / OWASP / ISO 27001), optionally video demo of attacks

05 · Who it's for

4 client types the offer is calibrated for

I don't work with SMB < 1M ₽/mo revenue (no 200k budget), with personal projects, or with students. I don't dive into classic industrial IT without AI — that's Positive Technologies' field.

Primary
60% revenue

Technical founders of B2B SaaS 20–100 people

With an AI feature in the product under pre-IPO DD pressure. Investors ask about AI security — DD standard since 2025. Launched a chatbot / RAG, sometimes 'gives weird answers'. MCP servers without review.

Why they pay

1 leak = product death + personal liability for the founder

Secondary
25% revenue

Performance agencies / media-buying houses ($500k–5M/mo)

AI tools accumulate conversion PII (FZ-152). Tracking systems leak via DNS history. CAPI without HMAC = fake conversions pass. Slava is one of you: he personally ran $1.34M ad budget in performance marketing.

Why they pay

1 ad account at $200k = a month down the drain

Tertiary
10% revenue

E-com 1000+ orders/mo with AI customer support

AI agent chats with customers — email / phone / address leaks to OpenAI. Voice bot jailbreak → 99% promo code. WB / Ozon + RKN actively audit since 2025.

Why they pay

Marketplaces block the selling account on breach

Quaternary
5%, large ticket

Government contractors / banks / fintech

From Jan 1, 2026: 187-FZ KII bans foreign software (Cursor / Claude / OpenAI = formal violation). Sales cycle 3–6 mo, FSTEC licenses required for deep pentests. Slava is an architect / consultant, not an FSTEC auditor. Only via a legal entity.

Why they pay

187-FZ trigger + long cycle = high ticket, low frequency

06 · How we're different

Narrow AI niche, not yet another generic pentest

I don't claim to replace Group-IB on perimeter / SIEM — we do different things. Comparison along the angle we work from:

vs

Group-IB / Positive Technologies

Their position

Classic perimeter / SIEM / anti-APT, $7–11B market. AI-security block = marketing. From 1.5M ₽, full IT perimeter

Our position

Narrow AI niche, 200–600k ₽. Targeted vs full SOC

vs

HackerOne / BugBounty.ru

Their position

Reactive crowd, no SLA, no accountability. You pay per finding separately

Our position

Proactive, single accountable expert. Report + recommendations + retainer. One contact

vs

Solo pentesters on Avito

Their position

Classic — Burp / Nessus / nmap. Don't know OWASP LLM Top 10. Don't understand prompt injection

Our position

I run AI in production 24/7. I've seen prompt injection in live traffic, not in a PDF

vs

Internal security teams

Their position

Enterprise IT (AD, perimeter, IDS). AI = gray zone, skills geared toward classical infra

Our position

External pair of eyes specifically for AI / automation. We complement, not replace the internal team

07 · Unfair advantages

Why me — at the intersection of 4 niche tracks

A combination of experience that's hard to replicate: senior enterprise development + production AI operator + media-buyer with a large budget + RU regulatory literacy.

01

Real production AI operator

10+ AI systems in production 24/7. Seen failure modes from the inside: cost overflow during regime change, GMM stuck in edge cases, indirect injection from an RSS feed, MCP server crash in production

02

$1.34M performance marketing budgets

Was a senior media-buyer at Syndicate Group + SweepStakes. I know fraud patterns from the inside, tracking mechanics, CAPI security — not theory, but field practice

03

7 years of enterprise

Baltic Shipyard, IPL, Asertiva. I understand how security works at large companies with long approval processes — I can speak the same language as a CTO / CISO

04

OSINT / attacker-side experience

Through arbitrage / affiliate work — I know how the attacker side thinks. Cloaker bypass, fingerprint evasion, IP rotation — these are working tools, not an article on Habr

05

Reads RU regulatory

FZ-152, 187-FZ KII, FSTEC orders, RKN guidelines — I actually read them, not retell from agencies. I know where compliance ends and real security begins

Next step

Secure your AI infrastructure

Start with Express Diagnostic for 25,000 ₽ — in 1 business day you'll get a clear view of the top-5 risks and whether you need a full audit.

Готовы начать?

Аудит за 5 000 ₽ — с конкретным отчётом и сметой

Расскажу что внедрить в вашем бизнесе в первую очередь, какая будет окупаемость, и нужен ли вообще AI для вашей задачи (иногда — нет).

Или просто напишите свой вопрос — отвечу в течение 2 часов