Skip to content
View Ananya-0306's full-sized avatar
:octocat:
Focusing
:octocat:
Focusing
140 followers · 28 following

Achievements

Achievement: StarstruckAchievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: StarstruckAchievement: QuickdrawAchievement: Pull Shark

Highlights

Block or report Ananya-0306

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Ananya-0306/README.md 
$ whoami
> ananya_chatterjee.exe

$ cat role.txt
> Security Engineer // AppSec · IAM Governance · AI Red Teaming

$ status
> [ONLINE] currently breaking LLM agents for fun and CVEs
Typing SVG

LinkedIn Hashnode GitHub followers

🛰️ root@ananya:~$ about

+ 5 years deep in AppSec, IAM governance, and DevSecOps
+ Now hunting vulnerabilities in things that talk back: LLMs and AI agents
+ Currently building open-source tooling to make AI attack surfaces visible
- Not interested in "the model is a black box" as an acceptable answer

I break things that talk in natural language for a living — prompt injection, leaky RAG pipelines, agents with way too much tool access. By day: IAM reviews, access governance, compliance automation. By night: making AI applications confess their architecture.

⚔️ Featured build

LLM Attack Surface Mapper

Most AI security tools fuzz the chat box and call it a day. LLMASM goes after the architecture hiding behind it — hidden RAG proxies, leaked system prompts, agent tool chains nobody documented, shadow APIs that never made it into the docs.

pip install llmasm-ananya
llmasm

🧩 AST agent-graph mapping  •  🕵️ shadow API fuzzing  •  ⚖️ LLM-as-a-judge verification  •  🔁 native SARIF for CI/CD

Repo Stars

🎯 Built for authorized testing and AI security research — point it at your own stack, not someone else's.

🧰 root@ananya:~$ loadout

security & grc OWASP ISO27001 PCI DSS SOC 2 NIST Zero Trust CVSS

identity & auth IAM OIDC SAML RBAC

cloud & infra AWS Azure AD Kubernetes OpenShift Docker Terraform

vapt & testing Burp Suite Metasploit Nmap OWASP ZAP Nexpose

siem & monitoring Splunk QRadar

automation & code Python Bash REST APIs n8n Linux GitHub

📡 root@ananya:~$ stats

$ tail -f intentions.log
[+] mapping AI attack surfaces
[+] writing it up on Hashnode
[+] always down to talk red teaming, IAM, or both
[+] connect ↑ — DMs open

⭐ if you've made it this far, go star llmasm — it remembers

Pinned Loading

  1. Jarvis-desktop-assistant Jarvis-desktop-assistant Public

    This is the New Jarvis AI Project it will do some functionality followed by user query.

    Python 8 4

  2. Ananya-0306 Ananya-0306 Public template

    https://github.com/Ananya-0306/Ananya-0306

    15 10

  3. hacker_roadmap hacker_roadmap Public

    📌 Your beginner pen-testing start guide. A guide for amateur pen testers and a collection of hacking tools, resources and references to practice ethical hacking and web security.

    26 4

  4. Instagram_Reels_downloader Instagram_Reels_downloader Public

    Here, let’s save reels from Instagram as they cannot be saved over the app itself, we can actually download them!

    Python 25 10

  5. Crack_any_password Crack_any_password Public

    We will see a basic program that is basically a hint to brute force attack to crack passwords. In other words, we will make a program to Crack Any Password Using Python. Show some ❤️ by starring th…

    Python 17 3

  6. llmasm llmasm Public

    LLM Attack Surface Mapper for AI Security Testing

    Python 1