Back to browse
GitHub Repository

Open-source AI vulnerability assessment and red-teaming engine using AST analysis and Docker runtime verification.

0 starsPython

ASL V6 – Open-source AST red-teaming engine for Python AI agents

by sivaaditya·Jul 27, 2026·2 points·0 comments

AI Analysis

MidBold Bet

AST filtering cuts false positives, but live Docker verification is slow.

Strengths
  • Docker runtime verification confirms exploits instead of guessing.
  • AST contextual filtering ignores test suites and docstrings.
  • Offline rule-based patching works without paid API keys.
Weaknesses
  • Future-dated CVEs (2026) undermine the credibility of the track record.
  • Running ephemeral containers for every snippet adds significant latency.
Category
Target Audience

AI security researchers and Python developers

Similar To

Bandit · Semgrep · Garak

Similar Projects

Security●●Solid

Z3r0 – Multi-agent red team collaboration platform

Docker-sandboxed agent orchestration for red teams joins a crowded automated pentesting space.

Niche GemShip ItBold Bet
yv1ing
201mo ago
AI/MLMid

OSymandias – Open-source runtime for multi-agent AI systems

Another agent orchestration layer competing with LangGraph, CrewAI, and AutoGen.

Ship It
andreisilva1
311mo ago