Skip to content
View Keedz1Off's full-sized avatar
🏠
Working from home
🏠
Working from home
0 followers · 1 following

Block or report Keedz1Off

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
Keedz1Off/README.md

Keedz1 | AI Agent & Application Security

I review security boundaries in AI agents, MCP integrations and tool-enabled applications. My background is in Web3 security: smart contracts, bridge flows and accounting invariants.

Method: map the flow → define invariants → build test scenarios → inspect results → verify fixes.

I use AI for code analysis, test development and automation. Reports distinguish confirmed behavior, security impact and remaining gaps.

Web3

AppSec

  • FastAPI mutation benchmark: an independent static auditor identified all five deliberately introduced defects. Attack scenarios were not validated over HTTP.
  • AppSec boundary workflow — a defensive FastAPI lab that turns an authorization matrix into pytest checks for note ownership, request validation, and token revocation. The runner also checks one Semgrep rule and saves Markdown, JSON, and JUnit reports. 14 tests passed locally. A GitHub Actions workflow is configured and awaits its first hosted run.

AI Agent Security

  • Browser Use: navigation-policy behavior; security impact remains unconfirmed.
  • FastMCP / MCP SDK: SSE error propagation and local verification of a proposed upstream fix.
  • Learn with GenAI: application resource-cleanup bug, local patch and regression tests.

Open to remote AI security / AppSec roles and contract research.

Telegram · Email

Pinned Loading

  1. fastmcp-auth-state-sse-case-study fastmcp-auth-state-sse-case-study Public

    Independent AI-assisted PrefectHQ FastMCP case study: auth, shared OAuth state, SSE error propagation, evidence and limitations.

  2. learn-with-genai-resource-lifecycle-case-study learn-with-genai-resource-lifecycle-case-study Public

    AI-assisted case study: confirmed SQLite resource-lifecycle bug, local fix, and regression tests. No confirmed DoS claim.

  3. browser-use-agent-security-case-study browser-use-agent-security-case-study Public

    Independent AI-assisted Browser Use trust-boundary case study: scoped local evidence, architecture, and calibrated conclusions.

    1

  4. web3-security-portfolio web3-security-portfolio Public

    Web3 security portfolio: bridge architecture, authorization boundaries, accounting invariants, Foundry testing, and evidence-qualified case studies.