Enoki
Actively maintained
≈ 1visits/mo
Little sign of use · estimate, read Oct 15, 2026
- For
- Teams shipping AI agents who need to test them for security and safety before release
- Activity
- Actively maintainedsite updated 3 weeks ago
- Company
- EthicGate BV · since 2026privacy policy · per Wikidata
- Runs as
- API
- Used for
- Find prompt injection and data leaks in a deployed agent
- Re-run attacks against each fix on every release
- Trigger attack runs from a CI pipeline before shipping
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantsenokilabs.ai ↗
Price not read
- Founded2026per Wikidata
- HeadquartersGhentper Wikidata
- Industrycomputer securityper Wikidata
- Run byEthicGate BVprivacy policy ↗
- Certifications they stateISO 27001 · GDPRsecurity page ↗
- Privacy policy updated2026-10-14privacy policy ↗
These are Enoki's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.
- MCP serverai.enokilabs/enokiverified in the MCP registry
- Stateanswers, requires sign-inchecked 2026-10-21
- Address to connectmcp.enokilabs.ai/mcp
- MCP docsdocs.enokilabs.aithe vendor's page ↗
This card as JSON, for your agent →
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1
Nexus Void Automated Penetration Testing
Runs continuous automated penetration testing and compliance verification with human-supervised attack agents.
42.9k - #2
Guardrails AI
Detects policy violations, hallucinations, and data leakage in large language model outputs at runtime.
11.5k - #3
Lakera
Detects and prevents prompt injection attacks, data leakage, and jailbreaks in AI applications with real-time threat detection.
2.9kActiveFree plan1993 - #4
Prompt Security
Monitors and secures AI agent deployments, detects prompt injection attacks, and flags sensitive data in LLM usage.
2.2kActive2023 - #5
Superagent Cloud
Runs security checks on AI agents, scanning code, dependencies, and runtime behavior for vulnerabilities.
2.2kActiveFrom $499/mo - #6
IndiciaMCP · sign-in
Runs OSINT searches across breach dumps, person records, social platforms and network infrastructure from one query, with an agent driving a browser.
2.1kActiveFrom $1 per use
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use Enoki for?
Sign in to leave a noteWhat is Enoki?
Attacks an AI agent's endpoint to find security and safety flaws, then re-runs the attacks on each release to verify fixes. It is listed in the Atlas under Security and made by EthicGate BV.
Who is Enoki for?
Teams shipping AI agents who need to test them for security and safety before release
Do people use Enoki?
Little sign of use: ≈ 1 visits/mo · estimate, 2026-10.
Is Enoki still maintained?
Actively maintained: site updated 3 weeks ago.
Who owns Enoki?
Enoki is run by EthicGate BV, per its privacy policy (2026-10-21).
Is Enoki safe?
We do not audit vendors. What Enoki publishes, read 2026-10-21: ISO 27001, GDPR stated on its security page.
What are alternatives to Enoki?
In Security, by use: Nexus Void Automated Penetration Testing, Guardrails AI, Lakera, Prompt Security, Superagent Cloud, Indicia.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.