ORACLENEP / APPLICATION & AI SECURITY

AI SECURITY

I research application and AI agent security, and build tools for reproducible security work.
Java / Spring code review, Agent / MCP trust boundaries, and coordinated vulnerability disclosure.

AppSecCode review, authorization, and root-cause analysis
AI / AgentTool permissions, MCP, and execution boundaries
DisclosureGHSA, public research, and remediation review
ToolingSecurity automation and upstream contributions

Selected Projects

Security tools and agent workflows, developed independently and with SoybeanSeclab. Repository stars as of November 14, 2026.

Team project★ 692

Phantom ↗

A browser extension for frontend asset discovery and API mapping during authorized security testing.

Recursive JavaScript scanning, configurable concurrency, batch API checks, custom rules, and structured exports.

JavaScriptBrowser extensionAppSec
Personal project★ 65

AgentFlowDesk ↗

A local Python CLI that organizes the work around AI coding agents, from task context to review.

Builds context packs and agent instruction files; records commands, logs, diffs, checks, and review reports. Current release: v0.1.0, CLI-first.

PythonCoding agentsLocal workflow
Team project · based on ARTEX★ 53

prtseek ↗

A four-role CTF agent system with asynchronous collaboration, shared budgets, and session artifacts.

Recent work improves evidence tracking, per-round records, interruption handling, HTTP observation, and experiment isolation.

GoAgent coordinationCTF

Update history → · Development notes →

Team project★ 48

prtstrike ↗

A lightweight Go command-and-control framework for authorized security labs and exercises.

Combines a web console, peer-node coordination, task and result management, file workflows, and Docker deployment.

GoDistributed systemsSecurity labs
Team project★ 2

JavaSecAtlas ↗

A Java / Spring audit workbench connecting route and permission context with source review.

v1.2.0 supports Semgrep / CodeQL SARIF import, heuristic checks, a local GUI, AI-assisted review, and JSON / Markdown / HTML / SARIF reports.

Java / SpringSARIFCode review

Security Research & Disclosure

Selected public findings and coordinated reporting. Advisory status checked November 14, 2026.

Published advisory

NocoDB

GHSA-hjgf-2f3h-4962 ↗

Server-side request forgery via integration remote fetch. The official advisory credits OracleNep as the reporter.

High · CVSS 8.5Published Nov 2, 2026

The advisory documents internal-network access and integration-secret exposure, with remediation across releases 2026.08.0 and 2026.10.1.

Public research report

DeepSeek Harness

Research into authentication and trust boundaries in the dsh web agent control plane, tested on 0.1.0-rc.6.

The report distinguishes local-process access from remote exposure when the service is configured to listen beyond loopback, and proposes authentication and authorization improvements.

Read discussion #853 ↗

Private reporting

Coordinated GHSA Submissions

Submitted vulnerability reports through GitHub's private security advisory workflow for Flowise and Strapi.

  • Flowise: one advisory in draft.
  • Strapi: three reports in triage.

These reports are not published advisories. Technical details remain private during coordination with maintainers.

CVE / CNVD References

Selected identifiers from individual and team vulnerability reporting.

CVE-2025-7181 CVE-2025-7175 CNVD-2026-10837CNVD-2025-17734

Upstream Contributions

Selected patches with public review and merge history.

Merged

VulnClaw #75

Added bounded recovery when the solve engine exhausts its open intents before completing the goal, with fallback exploration, CLI events, and regression coverage.

Review the patch ↗

Merged

PHP #22261

Documentation and test-comment maintenance for error conventions in ext/intl.

Review the patch ↗

Open for review

PHP #22223

Aligns request_parse_body() handling of max_input_vars with INI behavior, with PHPT regression coverage and compatibility notes.

Review the patch ↗

Research & Practice

From source review and reproducible findings to remediation and retesting.

Application Security

I review Java / Spring applications by tracing request entry points, permission checks, data flow, and dangerous operations. My tooling work connects source context with Semgrep / CodeQL findings and SARIF reports.

My practical experience includes authorized vulnerability research, incident triage, host-security checks, impact assessment, and remediation follow-up.

AI Agent Security

I study where agents cross trust boundaries: tool execution, MCP permissions, local control planes, and approval flows. I also work on recovery behavior, evidence records, and human review in agent-assisted security workflows.

Research notes document prerequisites and verification limits alongside findings.