@DanKornas: Security testing agents often lack security-specific workflows, reliable evidence collection, and auditability. Pentest…
Summary
PentesterFlow is an open-source terminal assistant for authorized offensive-security work that plans against scoped targets, uses pentesting tools, requests approval for sensitive actions, retains lessons across sessions, and writes evidence-backed findings. It includes built-in skills for recon and web vulnerabilities, session continuity features, local continuous learning, and Burp integration.
View Cached Full Text
Cached at: 08/09/26, 05:13 AM
Security testing agents often lack security-specific workflows, reliable evidence collection, and auditability.
PentesterFlow is an open-source terminal assistant for authorized offensive-security work that keeps the analyst in control.
It plans against a scoped target, uses pentesting tools, requests approval for sensitive actions, retains useful lessons across sessions, and writes evidence-backed findings.
Key features: • Built-in skills cover recon, web vulnerabilities, SSRF, SSTI, JWT, GraphQL, race conditions, takeover, Supabase, and deserialization. • Confirmed findings are saved as Markdown with evidence, impact, proof of concept, and remediation. • Session continuity includes saved history, persistent compacted memory, target state, resume recaps, context snapshots, and automatic five-minute snapshots. • The local continuous learning system stores successful workflows, failed assumptions, coverage gaps, and evidence requirements while redacting secrets before storage. • Burp integration can send selected requests into the CLI, queue them as scan tasks, import confirmed findings back into Burp, and preserve raw requests for replay.
PentesterFlow is licensed under Apache-2.0.
Link in the reply
Similar Articles
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
This paper presents a practical evaluation protocol for assessing AI pentesting agents in realistic, complex targets rather than simplified benchmarks. It uses LLM-based semantic matching, bipartite resolution, and continuous ground-truth to score vulnerabilities discovered, and releases expert-annotated ground truth and code.
@DanKornas: Security testing setup gets complicated fast. This repo maps the moving parts. HackerAI is a public GitHub codebase for…
HackerAI is a public GitHub codebase for an AI-powered penetration testing assistant, offering chat-driven workflows, agent-mode runtime with isolated execution, and guided local setup using Next.js, Convex, and Trigger.dev components.
Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines
This paper presents an execution-grounded red-team testing framework that probes the security boundaries of coding agents by embedding unsafe operations into routine software engineering tasks, achieving high rates of verified unsafe execution across multiple agent frameworks and model backbones.
vxcontrol/pentagi
PentAGI is an open-source AI-powered penetration testing tool that operates in a sandboxed Docker environment, featuring autonomous agents, integration with professional security tools, smart memory, and knowledge graph capabilities.
@XAMTO_AI: If you've used traditional manual penetration testing, you know!! Juggling multiple tools like Burp, Nmap, Metasploit, switching back and forth, spending hours on recon and exploit, writing PoCs by hand, writing reports until you question your life, false positives everywhere, while real vulnerabilities slip through... One developer couldn't take it anymore and open-sourced a...
Strix is an open-source AI penetration testing tool that uses autonomous AI agents to perform real vulnerability discovery and exploitation, generating working PoCs and compliance-ready reports. It supports multi-agent orchestration, CI/CD integration, and various LLMs, aiming to replace manual pentesting with AI-driven automation.