Agent-Field/sec-af
AI-native security auditor on AgentField that proves exploitability with verdicts, traces, and actionable evidence.
This project utilizes an adversarial agent architecture, employing separate "hunter" agents to find vulnerabilities and "prover" agents to rigorously verify them through a 4-agent chain, including taint tracing and exploit hypothesis generation. It filters findings in stages, progressively reducing 106 raw findings to 30 confirmed vulnerabilities by applying semantic similarity for deduplication and deep data flow analysis for verification. The auditor integrates with and targets the AgentField framework, processing repositories via a single API call for comprehensive security audits.
Stars
22
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Agent-Field/sec-af"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Nebulock-Inc/agentic-threat-hunting-framework
ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and...
AgentSeal/agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor...
cosai-oasis/secure-ai-tooling
The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in...
HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis....
oasm-platform/open-asm
Open-source platform for cybersecurity Attack Surface Management (OASM).