
Sunglasses
Open sourceActively maintained
1.9k installs/mo
Established
- For
- Developers and teams running AI agents who need to scan prompts, files, and tool metadata for injection
- Price
- Open sourcepricing page, read Oct 22, 2026
- Activity
- Actively maintainedrelease 4 days ago · site updated 6 days ago
- Company
- since 2026 · ~5 peopleper their About page
- Used for
- Scan untrusted repository files before an agent reads them
- Block prompt injection in web pages before model context
- Check MCP tool descriptors for poisoning before use
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantssunglasses.dev ↗
- Launched on Product Hunt on Jul 28, 2026Product Hunt ↗
Open source
- Founded2026per their About page ↗
- People~5per their About page ↗
- Privacy policy updated2026-10-20privacy policy ↗
- Security contactsecurity.txt
These are Sunglasses'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 serverio.github.sunglasses-dev/sunglassespublished by sunglasses-dev on GitHub
- Statenot asked yet
- MCP docssunglasses.dev/mcp-attack-atlasthe 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

SonatypeMCP · sign-in
Hosts artifact repositories and scans open source dependencies, blocking malicious or vulnerable components before they enter builds.
69.4kActiveFrom $1,200/yr2008 - #2

Snyk
Scans source code, open source dependencies, container images and infrastructure-as-code for vulnerabilities, and suggests fixes in the IDE, CLI and pull requests.
63.1kActiveFrom $25/mo2015 - #3

Lakera
Detects and prevents prompt injection attacks, data leakage, and jailbreaks in AI applications with real-time threat detection.
2.9kActiveFree plan1993 - #4

S4E
Scans websites for vulnerabilities including SQL injection, XSS, misconfigurations, and exposed credentials.
834ActiveFrom $119/mo2022 - #5

AI Security Guard
Detects malicious packages, scans prompts for injection attacks, and monitors agent runtime security.
675MaintainedFree2025 - #6

Mythos Agent
Scans code for security vulnerabilities using AI reasoning to generate hypotheses and rank findings by exploitability.
148MaintainedOpen source
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 Sunglasses for?
Sign in to leave a noteWhat is Sunglasses?
Scans prompts, files, repos and web pages for prompt injection and credential theft before an AI agent reads them. It is listed in the Atlas under Security.
Who is Sunglasses for?
Developers and teams running AI agents who need to scan prompts, files, and tool metadata for injection
How much does Sunglasses cost?
Sunglasses is open source, per its pricing page on 2026-10-22.
Is Sunglasses free?
Yes: Sunglasses is free, per its pricing page on 2026-10-22.
Do people use Sunglasses?
Established: 1.9k installs/mo (pypi).
Is Sunglasses still maintained?
Actively maintained: release 4 days ago · site updated 6 days ago.
What are alternatives to Sunglasses?
In Security, by use: Sonatype, Snyk, Lakera, S4E, AI Security Guard, Mythos Agent.
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.