This skill is a downstream specialization of the ctf-sandbox-orchestrator skill. It covers binary-heavy CTF challenges: reversing a sample, unpacking layers, inspecting memory dumps or captures, debugging crashes and verifying exploit primitives under sandbox assumptions.
It starts with passive triage (type, headers, sections, imports, strings, entropy), preserves the original artifact, keeps decoded and instrumented copies separate and ties each claim to an observable boundary. It routes to sibling skills for malware config, firmware, file parsers, PCAP and timelines. Replies are in Simplified Chinese unless English is requested.
What You Get
- A passive triage order for headers, sections, imports, strings, entropy and resources
- A native path checklist covering mitigations, loader, libc build, syscall surface and protocol framing
- Rules for keeping original, decoded, dumped and instrumented artifacts as separate files
- A routing list to eight narrower sibling skills
Common Use Cases
- Triaging a suspicious binary in a CTF reverse challenge
- Recording crash state and leak sources while verifying an exploit primitive in a lab
- Correlating files, registry, services and captures into one execution graph for a DFIR challenge
What Makes It Unique
It spans reverse, DFIR and pwn work in one entry point and then routes to narrower skills for malware config, firmware, parsers, source maps, container escape, PCAP, custom protocols and timelines. It requires replaying a primitive from a clean baseline before naming it, and it runs only after the orchestrator skill has set sandbox assumptions.
Under The Hood
The skill is instruction text only: a SKILL.md, one reference playbook and an agent config file that disables implicit invocation. It ships no scripts and does not itself fetch pages, call APIs, run commands or write files. Triage and debugging use the reverse engineering tools the user already has in the sandbox.