Sign InOpen Brain
GitHubGitHub RepoNeeds Review

zhaoxuya520/reverse-skill

A security skill router gives coding agents scoped, repeatable playbooks for reverse engineering and pentesting instead of ad hoc tool selection. Its case workflow also preserves evidence and findings.

GitHub
Open Source Open MarkdownOpen JSON
Source Summary

Reverse-skill routes agents across APK, binary, JavaScript, PCAP, CTF, and pentesting work. Its **MASTER-ROUTING** flow checks scope and authorization before action, inventories local tools, then selects a scenario playbook.

Practical Implication

Use it as a reference for security-agent harnesses: make authorization a hard gate, detect capabilities before planning, and record a timeline linking **Evidence→Finding→Path**. The repository includes platform setup and workflows for tools such as jadx, Frida, IDA, and Burp Suite.

Agent-Ready Context
Reverse-skill routes agents across APK, binary, JavaScript, PCAP, CTF, and pentesting work. Its **MASTER-ROUTING** flow checks scope and authorization before action, inventories local tools, then selects a scenario playbook.

Use it as a reference for security-agent harnesses: make authorization a hard gate, detect capabilities before planning, and record a timeline linking **Evidence→Finding→Path**. The repository includes platform setup and workflows for tools such as jadx, Frida, IDA, and Burp Suite.

This is a broad router pack, not evidence that its workflows produce correct findings. Tool availability, target authorization, sandboxing, and the licenses of included or invoked components still need independent review.
Connected Context · Feed7 Judgment

This makes security work a concrete routing problem: authorization, capability discovery, scenario selection, and evidence traceability are explicit stages. Against the prior candidates, it confirms that specialized playbooks can structure risky tool use, but also exposes two limits: an instruction-level authorization check is not an external security boundary, and a broad skill pack requires independent supply-chain review and outcome evaluation.

IT Admin for the AI Workforce — Sarthak Aggarwal, DecaworkReverse-skill’s authorization check is useful workflow discipline, while this candidate clarifies that enforceable identity, capabilities, revocation, and policy gates must sit outside agent instructions.We Vetted 2000 AI Skills Before They Reached Developers — Lucas Palma, NubankThe pack’s breadth and access to security tools make the candidate’s scanning, review, and distribution controls directly relevant before adoption.In Code They Act, In Proof We Trust — Erik Meijer, Leibniz LabsReverse-skill records Evidence→Finding→Path, while this candidate proposes a stronger execution boundary in which inspectable tool programs require machine-checkable safety proofs before side effects.addyosmani/agent-skillsBoth encode evidence-gated procedures, but reverse-skill applies the pattern to authorized security investigations rather than the general coding lifecycle.
Context Map
agentsecuritycoding#skills#harness-engineering#tool-use
Uncertainty
This is a broad router pack, not evidence that its workflows produce correct findings. Tool availability, target authorization, sandboxing, and the licenses of included or invoked components still need independent review.