lingbol088-spec

Guided reverse engineering workflow for binaries, firmware, mobile apps, scripts, document samples, protocol captures, and unknown artifacts. Use when Codex is asked to perform reverse engineering, malware or suspicious-file analysis, static or dynamic analysis, decompilation planning, vulnerability discovery, exploitability assessment, root-cause analysis, patch diffing, firmware analysis, Android/iOS app analysis, or to produce analysis reports, deep reverse reports, evidence-backed vulnerability reports, user-intent recovery for ambiguous reverse-engineering requests, and user-selectable next-step plans.

Guided workflow for authorized penetration testing, vulnerability validation, security reporting, CTF/local sandbox reverse engineering, and user-directed vulnerability research. Use when Codex is asked to run or plan a security assessment, triage a target or artifact, maintain pentest state, produce interim/final reports, choose next steps, perform deep authorized testing, validate vulnerabilities with controlled proof-of-concept evidence, or reverse engineer binaries, mobile apps, firmware, protocols, captures, scripts, document samples, or unknown artifacts as part of a local sandbox, CTF, training lab, owned-codebase audit, or authorized security review. Also use when the user invokes the activation phrase documented in references/prompting.md.

Detect missing capabilities during an AI agent task, search local skill folders plus configured GitHub skill registries, then install and validate the best matching skill before continuing. Use when an agent has loaded this skill and realizes another skill would make the current job safer, faster, or more accurate. Compatible with Codex by default and adaptable to other agent runtimes.