Навыки: Безопасность

Research external evidence for a product or project decision within a Byte workflow.

Avoid common C mistakes — memory leaks, buffer overflows, undefined behavior, and pointer traps.

<!-- Copyright (c) 2026 defconxt. All rights reserved. -->

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint...

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct...

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an...

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logg...

Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a chan...

Use when testing for web cache deception on an authorized assessment. Covers path confusion, cache key analysis, authent...

Hunt web cache poisoning, CDN cache poisoning, and cache deception attacks. Use when target uses a CDN (Cloudflare, Akam...

Use when testing web cache poisoning and web cache deception on an authorized engagement. Covers detecting cache layers...

cad reference tool

Use when the user wants to audit Cairo smart contracts for security vulnerabilities, scan Starknet contracts for felt ov...

Scans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messagi...

Create a Google Calendar event with title, time, and attendees

List upcoming Google Calendar events for a given timerange

Use when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", o...

Implement Controller Area Network (CAN) bus 2.0B / CAN-FD frames, arbitration IDs, and OBD-II automotive diagnostics.

Guides compliance with Canada's Personal Information Protection and Electronic Documents Act (PIPEDA, S.C. 2000, c. 5)....

An investigative and analytical agent that resolves issues using global and industry standards. Responsible for evaluati...

Assessing standards, regulatory controls, and legal-document coverage with cited evidence and proposed wording. Use for...

Accessibility audit and remediation for Canvas LMS courses. Scans content for WCAG-oriented issues, generates prioritize...

能力蒸馏工作流——从用户批准的强模型访谈或真实任务轨迹中提取非显然的判断规则，形成可审计的 judgment packet，再交给 skill-audit 和 skill-creator 决定是否落成可加载 skill。当用户说“蒸馏这个模...

Exhaustively execute every applicable CAPEC attack pattern.

Unified A-F grading and ship/no-ship decisions for the 6-skill radar family (5 companions + capstone). Aggregates handof...

Before any destructive or irreversible operation (rm -rf, DROP TABLE, DELETE, force push, branch deletion, truncate), or...

Use this skill when the user asks about cybersecurity for a trucking carrier — protecting ELD data, customer information...

Use when tracking security investigations, bug bounty findings, CTF leads, audit evidence, exploit chains, dead ends, or...

Skill for managing EVM wallets, transactions, and network helpers via cast; covers onboarding, checks, and operating pro...

Audit the fidelity of Eldritch Lich manuscript imports and automatically categorized data against a source text such as...

Use when auditing a CAV (Computer Aided Verification) submission for portal readiness, covering the four submission cate...

Terse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user...

Compressed communication mode. Drops filler, hedging, and narration while keeping full sentences and technical accuracy....

Persistent token-compression mode (~75% reduction) — now always-on by default. Strips filler while keeping code exact.

Manual Caveman-style code-review mode that produces concise findings with exact locations, evidence, impact, and a concr...

Automatically discover security skills when working with authentication, authorization, input validation, security heade...

AI Agent 安全設計模式 — 基於 Claude Code 七層縱深防禦架構的逆向分析。Use when: 設計工具安全機制、實作命令過濾、建構權限模型、設計 sandbox。

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or impleme...

Assess CCPA/CPRA compliance — consumer rights, opt-out, deletion, service provider agreements

Verify California Consumer Privacy Act compliance, consumer opt-out mechanisms, and service provider contracts.

Capture low-latency database commit log events using Debezium and Kafka Connect for real-time stream propagation.

Map calibrated_explanations capabilities to EU AI Act, GDPR, AI Liability Directive, and Product Liability Directive obl...

Für CE-Akte und technische Dokumentation: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko un...

Use for deciding whether an incoming DingTalk message needs a reply, reaction, clarification, handoff, or no action. Use...

Director ÚNICO del ecosistema de agentes de {{PROYECTO}}. Arma el Plan de Ejecución, aplica el flujo de curaduría de 5 p...