'defensive' 검색 결과

AI dynamic reasoning balance — maintaining grounded reasoning under cognitive pressure, smooth chain-of-thought coordination, and weight-shifting cognitive load across subsystems. Use at the beginning of a complex task requiring multiple coordinated reasoning threads, after a sudden context shift or tool failure, when chain-of-thought feels jerky, or when preparing for sustained focused work that requires all subsystems in alignment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI situational awareness — internal threat detection for hallucination risk, scope creep, and context degradation. Maps Cooper color codes to reasoning states and OODA loop to real-time decisions. Use during any task where reasoning quality matters, when operating in unfamiliar territory, after detecting early warning signs such as an uncertain fact or suspicious tool result, or before high-stakes output like irreversible changes or architectural decisions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Cybersecurity partner skill for acting as a practical security collaborator across architecture review, threat modeling, secure design, risk prioritization, defensive planning, vulnerability remediation, incident readiness, security roadmaps, and technical decision support. Use when the user wants an ongoing security advisor, reviewer, or second set of eyes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Authorized offensive security skill for ethical penetration testing, red-team planning, vulnerability validation, reconnaissance of owned assets, web/API/mobile/cloud assessment, report writing, remediation guidance, and lab-based security testing. Use only for systems the user owns or is authorized to test; focus on safe, scoped, legal assessment and defensive improvement.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Malware reverse engineering and suspicious artifact analysis skill for defensive triage, static analysis, dynamic analysis planning, unpacking strategy, indicators of compromise, behavior summaries, YARA/Sigma ideas, and remediation guidance. Use for suspicious binaries, scripts, documents, logs, memory artifacts, sandbox reports, and malware family analysis in isolated environments.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Authorized exploit development and vulnerability research skill for lab environments, CTFs, owned software, crash analysis, memory corruption, exploitability assessment, fuzzing results, proof-of-concept design, and remediation. Use for defensive validation and education; avoid real-world weaponization, stealth, persistence, evasion, or unauthorized targets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI and LLM red-teaming skill for evaluating prompt injection, jailbreak, data exfiltration, tool abuse, agent hijack, RAG poisoning, model denial of service, and unsafe tool-use chains in Gemini, Claude, GPT, and open-weight models. Use to build evaluation harnesses, attack corpora, defensive guardrails, and red-team reports for AI systems you own or are authorized to test.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Security Operations Center skill for alert triage, detection engineering, incident response, log analysis, threat hunting, SIEM queries, EDR investigation, timeline building, IOC handling, escalation notes, containment recommendations, and analyst-ready reporting. Use for blue-team operations, suspicious event analysis, and defensive cybersecurity workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Develops comprehensive threat actor profiles for APT groups, criminal organizations, and hacktivist collectives by aggregating TTP documentation, historical campaign data, tooling fingerprints, and attribution indicators from multiple intelligence sources. Use when briefing executives on sector-specific threats, updating threat model assumptions, or prioritizing defensive controls against specific adversaries. Activates for requests involving MITRE ATT&CK Groups, Mandiant APT profiles, CrowdStrike adversary naming, or sector-specific threat briefings.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review owned or authorized code for security using structure-first evidence: AST/structure maps, call graphs, complexity, Source/Sink flow, and defensive findings. Use when asked for security review, vulnerability review, AST structure map review, SAST triage, Source/Sink, taint flow, parser/scanner hardening, CI/CD security, LLM/agent tool boundary review, 脆弱性レビュー, 構造マップ, セキュリティレビュー.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Professional C: memory ownership, defensive programming, build hygiene, and systems-level correctness. Use when writing, reviewing, or maintaining C code.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Strengthen defensive security operations — detection engineering, hardening, monitoring, and continuous defense improvement.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

论文写作、修改、压缩和实验组织全流程中阻止【防御性写作】。把论文视为一场学术发布会， 而不是项目总结、实验日志或自我审查报告：识别这项工作最值得发表的价值，围绕它建立 最有利、最完整、最有说服力的叙事。不平均展示、不主动示弱、不写实验流水账、不替审稿人 攻击自己。 触发词：论文润色、论文修改、写摘要、写引言、写结论、压缩论文、rebuttal、回复审稿意见、 组织实验、论文AI味、防御性写作、心虚。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generalize published Spectre and remote microarchitectural research into passive target prerequisites, defensive review, and approval-gated local validation. Use for shared runtimes, JavaScript isolates, edge workers, serverless platforms, browser sandboxes, remote timing, cache side channels, speculative type confusion, or Dynamic Process Isolation analysis.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use for an adversarial red-team / blue-team / auditor review of an AI agent's CONFIG + behaviour (rules, skills, MCP, hooks, permissions) — attack-chain → defensive-gap list, not a code audit.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up authorized C2 simulation workflows and measure defensive detection outcomes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing, editing, or reviewing code, READMEs, docs, commits, changelogs, or any repo content. Pre-2020 human style — terse, opinionated, restrained, with project voice. Blocks the LLM tics (emoji headers, "leverage", "robust", "seamless", "delve", defensive bloat, type-hint overkill, marketing prose, "Whether you're X or Y", verbose error messages) catalogued from cpython, requests, flask, git, ripgrep, express, kubernetes, serde, and the Go stdlib. Triggers on "anti-ai", "human-style", "no slop", "write it like a human", or any time code/docs should look hand-written.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when designing defensive monitoring for agent systems whose risks accumulate across users, sessions, subagents, files, or tool calls. Adds online cross-context clustering with rare escalation, time-to-detect evaluation, provenance checks for control-like workspace content, and sanitized commits for persistent prompt-injection defense.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Core technical, safety, and maintainability rules for codebase edits. Trigger when: - Writing code, refactoring, modifying files, or creating unit tests. - Proposing commits, reviewing git history, or auditing code quality. - Modifying files in any programming language (e.g. *.go, *.rs, *.py, *.ts, *.js, *.c, *.cpp). - Prompt contains keywords: refactor, build, compile, lint, test, git, commit, rule priority, type safety, error handling, defensive programming.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Map advanced persistent threat (APT) group tactics, techniques, and procedures (TTPs) to the MITRE ATT&CK framework using the ATT&CK Navigator and attackcti Python library. The analyst queries STIX/TAXII data for group-technique associations, generates Navigator layer files for visualization, and compares defensive coverage against adversary profiles. Activates for requests involving APT TTP mapping, ATT&CK Navigator layers, threat actor profiling, or MITRE technique coverage analysis.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when performing cybersecurity operations - offensive or defensive - including threat detection and hunting, SOC operations, incident response, digital forensics and DFIR, malware analysis and reverse engineering, threat intelligence, cloud/container/network/application/API security, identity-access and zero-trust, OT/ICS and endpoint security, vulnerability and supply-chain management, DevSecOps, cryptography, AI security, compliance and governance, and red-team or penetration testing under signed rules of engagement; routes to one of 800+ technique playbooks mapped to MITRE ATT&CK, D3FEND, and NIST CSF.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Check code for standardization, readability, maintenance complexity, and defensive coding practices

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.