30 个 · 按相关度排序
Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.
中文简介正在准备中。当前显示英语简介。
Simulate supply chain and adversarial machine learning attacks by injecting poisoned data or targeted backdoors into training and fine-tuning datasets. Use this skill when assessing the integrity controls of MLOps pipelines or evaluating the resilience of AI models against highly targeted, stealthy manipulation intended to alter model behavior on specific triggers.
中文简介正在准备中。当前显示原文说明。
Assess Microsoft Entra ID with AADInternals during authorized security testing. Examine publicly exposed tenant information, API access, and federation weaknesses, including Golden SAML, a token forgery technique, then document evidence and recommendations for stronger identity protection.
中文简介正在准备中。当前显示英语简介。
Examine Linux authentication logs, shell history, SSH keys, scheduled tasks, and system settings to investigate a compromise. Help reconstruct activity, identify ways attackers maintain access, and document suspicious accounts, files, and configuration changes.
中文简介正在准备中。当前显示英语简介。
Plan persistence testing for authorized Windows and Linux security exercises, examining how access can survive logons or restarts. The skill compares mechanisms by privilege level and environment, with validation steps, detection indicators, and cleanup considerations.
中文简介正在准备中。当前显示英语简介。
Tax optimization strategies analyzer. Identifies high-impact tax savings across tax-loss harvesting, tax-advantaged accounts (401k, IRA, HSA), Roth conversions, backdoor and mega backdoor Roth, charitable giving, business deductions, capital gains harvesting, state tax minimization, and estate tax planning. Produces FINANCE-TAXES.md with prioritized strategies and estimated annual tax savings.
中文简介正在准备中。当前显示原文说明。
Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.
中文简介正在准备中。当前显示原文说明。
Identify poisoned training data and backdoored models across the ML pipeline.
中文简介正在准备中。当前显示原文说明。
Run Microsoft Entra ID tenant reconnaissance, token acquisition and manipulation, and federation backdoor testing with the AADInternals PowerShell toolkit to validate identity-attack resilience.
中文简介正在准备中。当前显示原文说明。
Comprehensive persistence tradecraft for authorized red team engagements covering Windows and Linux mechanisms. Windows techniques include registry Run/RunOnce keys, scheduled tasks, WMI event subscriptions, DLL search order hijacking, COM object hijacking, Startup folder drops, service creation, Security Support Provider (SSP) DLL injection, and Active Directory persistence (AdminSDHolder abuse, DCShadow, Golden Ticket, Silver Ticket, Skeleton Key, SID History injection). Linux techniques include cron and at jobs, systemd timers and services, SSH authorized_keys injection, shell profile backdoors (.bashrc/.bash_profile), PAM module backdoors, LD_PRELOAD hijacking, kernel module rootkits, web shells, and Git hook abuse. Provides operator-ready command sequences for SharPersist, Impacket ticketer, schtasks, sc.exe, crontab, and systemctl with OPSEC considerations for each method. Maps to MITRE ATT&CK T1547 (Boot or Logon Autostart), T1053 (Scheduled Task/Job), T1546 (Event Triggered Execution), T1556 (Modi...
中文简介正在准备中。当前显示原文说明。
Guide malware cleanup on infected Windows and Linux systems after containment and investigation. Covers removing malicious files and mechanisms that preserve attacker access, rotating credentials, patching entry points, and documenting validation results before recovery.
中文简介正在准备中。当前显示英语简介。
Inspect Linux scheduled tasks, services, shell profiles, shared library settings, and SSH keys for mechanisms that maintain attacker access. Correlate findings with audit logs to produce a timeline, risk scores, and remediation commands.
中文简介正在准备中。当前显示英语简介。
Assess AWS, Azure, and GCP environments by identifying identities, permissions, and paths to broader access or data exposure. Covers cloud storage, secrets, cross-account trust, and CI/CD, the automated systems used to build and deploy software.
中文简介正在准备中。当前显示英语简介。
Causal inference framework for answering "does X cause Y?" beyond correlation. DoWhy (Microsoft Research) provides the identify-estimate-refute loop: define a causal graph (DAG), identify the causal effect using backdoor/frontdoor/instrumental variable criteria, estimate treatment effects with multiple estimators, and validate results with automated refutation tests. Use when: distinguishing causation from correlation, estimating treatment effects (ATE, ATT, CATE), designing and analyzing A/B tests with confounders, using instrumental variables, performing counterfactual reasoning ("what would have happened if..."), validating causal claims with sensitivity analysis, working with observational data where randomization is impossible, or any analysis where the question is "what is the CAUSAL effect of X on Y" rather than just "how do X and Y relate?"
中文简介正在准备中。当前显示原文说明。
Production-grade Bayesian causal inference with PyMC, CausalPy, and DoWhy. Enforces DAG-first thinking, mandatory user checkpoints for assumptions, design-specific refutation, and defensible reporting with causal language guardrails. Trigger on: causal inference, causal effect estimation, treatment effects, counterfactuals, difference-in-differences (DiD), synthetic control, regression discontinuity (RDD), interrupted time series (ITS), instrumental variables (IV), propensity scores, DAGs, causal graphs, confounders, backdoor criterion, do-calculus, interventional distributions, pm.do(), pm.observe(), CausalPy, DoWhy, mediation analysis, refutation, sensitivity analysis, parallel trends, placebo tests, or any question of the form "does X cause Y" or "what is the effect of X on Y."
中文简介正在准备中。当前显示原文说明。
Use when attacking or auditing a CI/CD pipeline or software supply chain — pwn requests, poisoned pipeline execution, compromised/mutable-tag actions, dependency confusion, registry worms, runner backdoors, OIDC trust abuse, SLSA/provenance
中文简介正在准备中。当前显示原文说明。
Personal finance planning — 5-pillar framework (cash flow, net worth, debt, emergency fund, investing), tax optimization, insurance review, retirement planning (FIRE, 4% rule, Mega Backdoor Roth), and document retention.
中文简介正在准备中。当前显示原文说明。
Systematically remove malware, backdoors, and attacker persistence mechanisms from infected systems while ensuring complete eradication and preventing re-infection.
中文简介正在准备中。当前显示原文说明。
Identify and exploit vulnerabilities in the AI Supply Chain by injecting malicious models, datasets, or dependencies. Use this skill to simulate advanced persistent threats (APTs) compromising Hugging Face repositories, manipulating pre-trained weights (Model Poisoning), and exploiting insecure deserialization during model loading (e.g., Pickle files).
中文简介正在准备中。当前显示原文说明。
Hunts for Linux persistence by inspecting cron, systemd units, shell rc files, SSH authorized_keys, and common autostart locations for attacker-added entries. Activates for requests to hunt Linux persistence, audit cron/systemd for backdoors, or find unauthorized autostart and authorized_keys entries.
中文简介正在准备中。当前显示原文说明。
Hunts for malicious WMI permanent event subscription persistence by correlating __EventFilter, CommandLineEventConsumer/ActiveScriptEventConsumer, and FilterToConsumerBinding records from Sysmon Event IDs 19/20/21 or WMI repository exports. Activates for requests to hunt WMI persistence, detect event consumer backdoors, or analyze WMI subscription telemetry.
中文简介正在准备中。当前显示原文说明。
Analyzes suspected webshells (PHP, ASPX/ASP, JSP) by detecting dynamic-execution sinks, input-to-sink data flow, and common encoder/obfuscation chains, then decoding obvious layers to reveal the command interface. Activates for requests to analyze a webshell, identify a PHP/ASPX/JSP backdoor, or deobfuscate server-side malicious scripts.
中文简介正在准备中。当前显示原文说明。
Detect and analyze Linux persistence mechanisms including crontab entries, systemd service units, LD_PRELOAD hijacking, bashrc modifications, and authorized_keys backdoors using auditd and file integrity monitoring
中文简介正在准备中。当前显示原文说明。
MetaBackdoor trains the model to activate hidden behavior when the total token count crosses a speci
中文简介正在准备中。当前显示原文说明。