Skip to content
VC
Service · Flagship offering

Defensive diagnostic of AI systems and infrastructure in production

I stress-test your AI agents, retrieval over your own documents (RAG), MCP servers and infrastructure per OWASP LLM Top 10 — finding what a standard penetration test misses.

01
Built for the AI layer itself

Prompt injection — when the model is fed someone else's instruction and follows it. Plus RAG poisoning, MCP tool poisoning, token bomb — vectors that aren't in Burp / Nessus

02
A practitioner's lens, from running these systems

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

From 20M ₽ plus 1–3% of revenue on a repeat PII leak. Foreign-software limits under CII rules follow the owner of a significant object

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.

What such a diagnostic actually looks for, which fine amounts are written into the statutes, and how to run a minimal check yourself in twenty minutes — in the personal data and LLMs deep dive.

Tier 1

Express Security Diagnostic

45,000 ₽
1 business day

Quick entry check: shortened checklist, one live attack, PDF with top-5 risks. A clear entry point before the 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 400,000 ₽
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

400–1,100k ₽ range depending on scope and number of AI agents

Tier 3

Continuous Security Engagement

from 52,000 ₽/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 52k: monthly re-scan, CVE alerts in Telegram, 2h Q&A
  • Basic +: quarterly report on risk dynamics
  • Pro 130k: + 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. 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 the full audit 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 7.8

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 the full audit 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 + disaster-recovery 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 the full audit 20%
C15 Critical

FZ-152 compliance

Geo storage (PII of Russian citizens on RU territory), sub-processors, RKN registry. Fines under art. 13.11 of the Administrative Code: 3–15M ₽ for a leak depending on database size, 1–3M ₽ for failing to notify the regulator, and 1–3% of revenue on a repeat leak but never below 20M ₽

C16 Critical

Critical-infrastructure readiness

The restriction follows the owner of a significant CII object; a whole industry does not fall under it. Presidential Decree No. 166 of 30.03.2022, plus the duty to run registry-listed Russian software on significant CII objects, in force since 1 September 2025 (Federal Law No. 58-FZ of 07.04.2025). If your object falls under it, Cursor / Claude / OpenAI on it is a formal violation. Alternatives: GigaChat on-prem, YandexGPT, Continue.dev

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 the full audit 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

Served-page integrity checks, tracker 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 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 — 3–15M ₽ under art. 13.11 of the Administrative Code
  • 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

Full audit report — 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

The Full Audit and the retainer are built for companies above 1M ₽/mo in revenue: below that there is rarely a 400k budget, and the Express Diagnostic at 45,000 ₽ is the sensible place to start. I don't take on personal projects or student work. I take on systems that have an AI layer; classic industrial IT is 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. I'm one of you: I personally ran a $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

Significant CII objects have had to run registry-listed Russian software since 1 September 2025 (Federal Law No. 58-FZ of 07.04.2025), and procurement / use of foreign software is limited by Presidential Decree No. 166. The duty follows the owner of the object: if the object falls under it, Cursor / Claude / OpenAI on it is a formal violation. Sales cycle 3–6 mo, FSTEC licenses required for deep pentests. I'm an architect / consultant; I do not run FSTEC-line audits. I only work through a legal entity.

Why they pay

CII requirements force action, but the cycle is long: high ticket, low frequency

06 · How we're different

Our profile is a narrow AI niche

Perimeter and SIEM are Group-IB's work, 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, 400–1,100k ₽. Targeted review of a specific system

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

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 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, an algorithm stuck on an edge case, indirect prompt injection from an RSS feed, MCP server crash in production

02

$1.34M performance marketing budgets

Was a senior media-buyer at two large media-buying teams, names under NDA. I know fraud patterns from the inside, tracking mechanics, CAPI security — from daily hands-on work

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

The attacker's point of view

Years in performance marketing mean a daily fight against bots, fake engagement and traffic fraud. From inside the industry I saw how advertising and web systems get abused, so I test a system by asking "how would I break this myself"

05

Reads RU regulatory

FZ-152, 187-FZ KII, FSTEC orders, RKN guidelines — I read the primary sources myself. I know where compliance ends and real security begins

Next step

Secure your AI infrastructure

Start with Express Diagnostic for 45,000 ₽ — in 1 business day you'll get a clear view of the top-5 risks and whether you need a full audit.

Ready to start?

The 9,900 ₽ audit — with a concrete report and quote

I'll tell you what to deploy in your business first, what the payback looks like, and whether you need AI for the task at all (sometimes you don't).

Or just send your question — I reply within 2 hours