
aisecplus-week01-servicenow-ai-security-incident
Research and analysis of the ServiceNow Virtual Agent vulnerability (CVE-2025-12420), including attack flow, MITRE ATT&CK mapping, detection…

Research and analysis of the ServiceNow Virtual Agent vulnerability (CVE-2025-12420), including attack flow, MITRE ATT&CK mapping, detection…

PoC for CVE-2025-62593: unauthenticated RCE in Ray (CISA KEV). Stdlib-only Python.

Expose and detail an unauthenticated stored XSS vulnerability in the Google Cloud Vertex AI Python SDK affecting versions 1.98.0 to 1.130.9.

Technical analysis of the LangChain serialization injection vulnerability CVE-2025-68664.

Exploit for Langflow AI Remote Code Execution (Unauthenticated)

Pre-launch security checklist for AI-generated apps (Lovable, v0, Bolt, Cursor). 69 checks covering Supabase RLS, exposed keys, and prompt injection.…

Artefacts for blog post on finding CVE-2025-37899 with o3

Docker Compose lab reproducing CVE-2026-33626 SSRF in LMDeploy's vision-language image loader. Compares vulnerable (0.12.0) and patched (0.12.3)…

A testing framework to identify and demonstrate deserialization vulnerabilities in LangChain Core (<0.3.81). Educational use only


Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.

Provenance-aware Linux kernel vulnerability research harness used in the investigation of CVE-2026-53075

A tool that checks if a TorchServe instance is vulnerable to CVE-2023-43654

Forensic Analysis and Local Replication of the OpenAI-Artifactory Privilege Escalation Incident (CVE-2026-65616)

vulnerability in CVE 2025-9998 and solution for those vulnerability with help artificial intelligence

Reproducible vulnerable and fixed GitHub Actions fixtures for agentic workflow injection (CVE-2026-44246), with measured detector coverage and…

A PoC for CVE-2024-3660. Arbitrary Code Execution in Keras.

PowerShell-based detection and remediation toolkit for CVE-2025-32711 (EchoLeak), a critical zero-click AI command injection vulnerability in…