Security · For devops and sre engineers

L1 trigger - audits peer-to-peer networking for DoS vectors (resource exhaustion, amplification), eclipse attack susceptibility, and discovery table poisoning (Kademlia/devp2p).

PlamenTSV/plamen

Trigger HASMULTICONTRACT flag in templaterecommendations.md (recon detects 2+ in-scope contracts/modules sharing parameters or formulas) - Agent Type general-purpose (standal...

PlamenTSV/plamen

A skill your agent uses when opening or updating a GitHub pull request after Phase 5 of /compliance:analyze-cve has applied and verified a CVE fix locally.

openshift-eng/ai-helpers

CRITICAL: Never modify files in content-addressable storage systems where the filename IS the content hash (SHA256, IPFS CID, etc.).

divinevideo/divine-mobile

Assess identity trust topology, assurance boundaries, issuer and relying-party responsibilities, and failure containment before testing a specific authentication or authorization mechanism.

cyberful/cyberful

Audit where access policy is decided and enforced across source, configuration, services, caches, jobs, and data stores, including deny behavior and decision-input integrity.

cyberful/cyberful

Route a cloud-native security audit across effective IAM, infrastructure as code, build and release paths, containers, Kubernetes, serverless workloads, secrets, event sources, and control-plane…

cyberful/cyberful

Operate a managed Firefox/Marionette laboratory for privileged chrome-context experiments, content automation, real WebDriver windows, permission readback, and synthetic X11 clipboard controls.

cyberful/cyberful

Use the release-embedded MITRE ATT&CK snapshot as a threat-informed reasoning lens without allowing the framework to constrain novel vulnerability discovery.

cyberful/cyberful

Test account and authenticator recovery as an assurance transition, including proofing, channel changes, support overrides, replay resistance, and post-recovery invalidation.

cyberful/cyberful

Route file-ingestion security work across processing pipelines, deserialization and object binding, and SOAP or XML services.

cyberful/cyberful

Route HTTP intermediary testing across request normalization, web-cache behavior, and offline traffic evidence.

cyberful/cyberful

Test identity linking, invitation, merge, provisioning, deprovisioning, and account-association ceremonies for proof-of-control, tenant binding, uniqueness, lifecycle, and rollback failures using…

cyberful/cyberful

Test promotions, referrals, quotas, inventory, and entitlement invariants through authorized, bounded, reversible experiments with tester-controlled accounts and assets.

cyberful/cyberful

Scan networks to discover devices, gather MAC addresses, vendors, and hostnames.

sundial-org/awesome-openclaw-skills

A skill your agent uses when drafting an ACM CCS rebuttal during the HotCRP author-response window, covering threat-model defenses, adaptive-attack objections, ethics and disclosure questions…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when deciding whether a security project fits ACM CCS versus IEEE S&P, USENIX Security, NDSS, PETS, or a crypto/theory venue, identifying the security contribution type, and…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when drafting the IEEE S&P (Oakland) rebuttal for second-round papers or the response plan for a Revise decision, including triaging reviews under the ~5-day window…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when deciding whether a security or privacy project belongs at IEEE S&P (Oakland), including the threat-model test, SoK fit, routing among USENIX Security, CCS, NDSS, PETS…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when deciding what lives in the ISSTA 18-page body versus the artifact and any appendix, covering the no-unlimited-appendix reality, what reviewers will and will not open…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when designing or auditing the evaluation of a USENIX Security Symposium paper — building threat-model-faithful experiments, adaptive-attacker analysis for defenses…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when reasoning about how a USENIX Security Symposium cycle actually decides — early-reject notifications, multi-round reviewing, the retirement of Major Revision in favor of…

brycewang-stanford/Awesome-Journal-Skills

For a batch of findings from a non-security audit tool (<audit-tool — ruff / flake8 / mypy / pylint / CodeQL / Apache Verum / Apache Caer / equivalent; full list in the body) against <upstream…

apache/magpie

Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values

LeoYeAI/openclaw-master-skills

Java 源码文件操作类漏洞审计。当在 Java 白盒审计中需要检测文件相关漏洞时触发. An agent skill from wgpsec/AboutSecurity.

wgpsec/AboutSecurity

Java 框架特定漏洞源码审计。当在 Java 白盒审计中需要检测框架层面的已知漏洞模式时触发. An agent skill from wgpsec/AboutSecurity.

wgpsec/AboutSecurity

Java 源码序列化类漏洞审计。当在 Java 白盒审计中需要检测序列化/反序列化相关漏洞时触发. An agent skill from wgpsec/AboutSecurity.

wgpsec/AboutSecurity

PHP 源码序列化与模板类漏洞审计。当在 PHP 白盒审计中需要检测反序列化、XML 解析或模板注入漏洞时触发. An agent skill from wgpsec/AboutSecurity.

wgpsec/AboutSecurity

主动式全流程资产侦察。当需要对目标进行从零到漏洞发现的完整侦察、渗透测试的第一阶段、或需要全面了解目标攻击面时使用。覆盖子域名枚举→端口扫描→存活检测→指纹识别→POC 扫描的完整链条

wgpsec/AboutSecurity

Audit the conversation and the project for what could have gone better, then turn the generalizable lessons into committed improvements in the repo that hosts this skill.

forefy/.context

Audit codebase to uncover critical issues explicitly without false positives

forefy/.context

Screen a weather- or event-triggered demand spike for Amazon product opportunities by checking local supply-capacity gaps, installation or usage-friction barriers, and one's own supply-chain…

xjli360/sealeap-amazon-skills

Audits dependency supply chains for bad versions, lockfile drift, and artifact integrity.

athola/claude-night-market

Review application and infrastructure changes for exploitable security risks by tracing assets, trust boundaries, attacker-controlled input, authorization, sensitive data, and dangerous sinks.

hashgraph-online/awesome-codex-plugins

セキュリティ観点の通常レビューエージェント. An agent skill from hashgraph-online/awesome-codex-plugins.

hashgraph-online/awesome-codex-plugins

Repository または subsystem を対象に、source-only で明示的なセキュリティ監査を行う entry skill。

hashgraph-online/awesome-codex-plugins

完成した差分・PR・検証証拠に残る Unknown（未確認の前提・調査されていない影響・ 不足している証拠）を横断合成する evidence-sufficiency のメタ観点。個別 defect の 検出は既存 skill へ委譲し、本 skill は「そのリスク種別を調査した証拠が残っているか」 の meta 評価のみを行う。通常は finding verification 後の…

hashgraph-online/awesome-codex-plugins

Audit npm dependencies for security vulnerabilities, outdated packages, and unused dependencies.

OneWave-AI/claude-skills

A skill your agent uses to run real static analysis over a diff or repo before shipping — Semgrep, CodeQL, secret scanning, dependency CVEs — and triage the findings into what must be fixed now…

OneWave-AI/claude-skills

反作弊对抗分析：EAC/BattlEye 驱动、内存校验、检测机制还原. An agent skill from dslsdzc/rev-skills.

dslsdzc/rev-skills

加密数据还原：定位解密函数、写解密脚本. An agent skill from dslsdzc/rev-skills.

dslsdzc/rev-skills

加密算法识别：常量表指纹、自定义加密模式. An agent skill from dslsdzc/rev-skills.

dslsdzc/rev-skills

检测规避/EDR 对抗分析：AMSI/ETW 绕过、无文件、lolbin 链. An agent skill from dslsdzc/rev-skills.

dslsdzc/rev-skills

勒索软件分析：加密识别、勒索信、解密恢复思路. An agent skill from dslsdzc/rev-skills.

dslsdzc/rev-skills

Security review checklist for construction software systems.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Run security scans and vulnerability checks. An agent skill from enuno/unifi-mcp-server.

enuno/unifi-mcp-server

Linux kernel security skill for LSM, hardening, and exploit mitigations.

mohitmishra786/low-level-dev-skills

Deep architectural context building for security audits. An agent skill from sendaifun/skills.

sendaifun/skills