查找技能

Guide bug bounty work from checking authorized scope and discovering assets to testing web and AI features. Validate practical impact, investigate related weaknesses, and organize reproducible evidence into a vulnerability report.

中文简介正在准备中。当前显示英语简介。

• Planning research for a new bug bounty target
• Reviewing source code for security weaknesses
• Testing chatbot and AI feature security

Assess what discovered cloud credentials allow across AWS, Azure, GCP, and Kubernetes. The skill guides identity checks, permission review, and paths to higher privileges, then helps document impact, activity, and cleanup within the engagement's agreed scope.

中文简介正在准备中。当前显示英语简介。

• Assess permissions granted by discovered cloud credentials
• Review role trust and access across cloud accounts
• Check permissions assigned to anonymous Cognito identities

Investigate cloud configuration weaknesses across AWS, GCP, and Azure, including public storage, exposed services, and leaked credentials. Find candidates in public information and JavaScript, then verify data access and permissions to establish practical impact.

中文简介正在准备中。当前显示英语简介。

• Checking public access to S3, GCS, and Azure Blob storage
• Reviewing exposed serverless and managed services
• Assessing CloudWatch RUM guest role permissions

Assess Kubernetes and Docker security across exposed APIs, access permissions, service account tokens, and container boundaries. Use actual data reads or command output to establish impact and distinguish information exposure from broader compromise.

中文简介正在准备中。当前显示英语简介。

• Reviewing exposed Kubernetes APIs and kubelet ports
• Checking RBAC permissions and service account tokens
• Assessing etcd and Dashboard data exposure

Prepare a /hunt security assessment by loading skills for the selected mode and, for red team work, detected platforms. Summarize the loaded set, select reporting formats, and check supplied credentials before authenticated testing.

中文简介正在准备中。当前显示英语简介。

• Preparing skills for a red team assessment
• Loading a web application security testing skill set
• Prioritizing platform skills across multiple hosts

Guide bug bounty work from asset discovery to validation and reporting, while resolving local locations of security tools, wordlists, and cloned projects. It covers web and AI security testing with an emphasis on demonstrated impact.

中文简介正在准备中。当前显示英语简介。

• Locate installed security tools and wordlists
• Plan reconnaissance within a program's scope
• Investigate related weaknesses and their combined impact

Assess Azure, AWS, and GCP security through resource inventories, authentication checks, permission reviews, and misconfiguration testing. Supports authorized assessments that document exposed credentials, rate risks, and recommend improvements for each cloud platform.

中文简介正在准备中。当前显示英语简介。

• Inventorying cloud resources and permissions
• Checking for exposed credentials and secrets
• Testing the impact of cloud misconfigurations

Deploy code changes to a live hero training run by starting a new run from a permanent checkpoint, a saved training state. Compare matching training steps against agreed criteria and roll back if the trial fails.

中文简介正在准备中。当前显示英语简介。

• Deploy backend or optimizer changes to a live training run
• Compare loss and throughput across matching training steps
• Rehearse checkpoint handoff and rollback procedures

Operate Iris jobs and tasks, from submission and monitoring to debugging and recovery. The skill also guides scheduling checks, coordination between clusters, controller deployments, development GPU or TPU reservations, and investigation of stuck CoreWeave pods.

中文简介正在准备中。当前显示英语简介。

• Monitoring Iris jobs and investigating failures
• Diagnosing scheduling delays and cross-cluster coordination
• Deploying or rolling back controllers

Diagnose failed canary ferry runs, automated checks for failures or regressions, when invoked by CI with the required context. It gathers logs, classifies the cause, and files a GitHub issue with supporting evidence.

中文简介正在准备中。当前显示英语简介。

• Investigate GPU or TPU canary failures triggered by CI
• Distinguish infrastructure failures from training or metric problems
• File a GitHub issue with logs and run context

Structure authorized container security tests covering Docker escape, Kubernetes privilege escalation, image vulnerabilities, and network isolation. This skill defines scope, alternative investigation paths, and evidence requirements for reporting demonstrated access and its impact.

中文简介正在准备中。当前显示英语简介。

• Define the scope of an authorized container security test
• Review evidence of host access or increased cluster permissions
• Consider other paths when container checks stall

Build a planned feature by following an existing task list and technical plan. The skill respects task dependencies, runs tests before related implementation where applicable, records progress, and checks the completed work against the specification.

中文简介正在准备中。当前显示英语简介。

• Implementing a feature from an existing task breakdown
• Developing with tests before the related implementation
• Tracking completed tasks and checking the final result

Build production systems for machine learning models, from deployment to monitoring and retraining. The skill also guides LLM integration and retrieval augmented generation, which uses retrieved information to support answers, with scripts and architecture references.

中文简介正在准备中。当前显示英语简介。

• Deploying machine learning models to production
• Setting up model monitoring and retraining
• Building applications that answer using retrieved information

Plan experiments, analyze data, and build and evaluate predictive models. The skill also covers explaining findings to stakeholders and designing production workflows for model deployment, monitoring, and retraining to support business decisions.

中文简介正在准备中。当前显示英语简介。

• Designing experiments and A/B tests
• Preparing model inputs and evaluating predictions
• Planning model deployment and monitoring

Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.

中文简介正在准备中。当前显示英语简介。

• Choose a lower-cost cloud for GPU training
• Run long training jobs with recovery after interruptions
• Configure distributed training across multiple machines

Design and improve prompts and structured responses for AI applications. The skill also guides evaluation, retrieval augmented generation, which uses retrieved material to inform answers, and agent architecture, with references and scripts for production workflows.

中文简介正在准备中。当前显示英语简介。

• Improving prompts and response formats
• Evaluating answers based on retrieved documents
• Designing AI agent systems

Build image and video AI systems for object detection and segmentation, which identifies separate image regions. The skill covers custom model training, dataset pipelines, inference optimization, real-time processing, and deployment and monitoring in production.

中文简介正在准备中。当前显示英语简介。

• Developing object detection and image segmentation systems
• Training custom vision models with project data
• Optimizing inference for real-time video processing

Design and automate machine learning workflows from data preparation through training, validation, deployment, and monitoring. Provides guidance and templates for reproducible experiments, quality checks, gradual model rollouts, and restoring a previous model when problems occur.

中文简介正在准备中。当前显示英语简介。

• Building a new machine learning pipeline
• Creating reproducible training workflows
• Adding quality checks before model deployment

Review code or pull requests for likely bugs, readability, maintainability, and risks to existing behavior. Supporting scripts and reference checklists help analyze code quality, identify missing tests, and organize findings into a review report.

中文简介正在准备中。当前显示英语简介。

• Reviewing a pull request for bugs and risks to existing behavior
• Checking code readability and maintainability
• Finding test coverage gaps and preparing a review report

Set up Auto Ontology with Helm or Docker Compose, or connect an agent to an existing deployment through MCP, an agent connection protocol. Guides database connections, readiness checks, and troubleshooting for startup and sign-in problems.

中文简介正在准备中。当前显示英语简介。

• Installing Auto Ontology on Kubernetes
• Running the stack on one machine with Docker Compose
• Connecting an agent to an existing deployment

Create videos of anomalous events, such as falls or fires, from seed images using Cosmos3. Run a Kubernetes workflow that generates clips, automatically labels them, and builds an anomaly dataset, with progress monitoring and result retrieval.

中文简介正在准备中。当前显示英语简介。

• Generate fall or fire clips from seed images
• Build synthetic datasets for safety and surveillance
• Automatically label generated event videos

Build custom Kubernetes Airflow workflows for PAIDF Orchestration by combining existing processing stages. Produces workflow code, deployment manifests, input validation models, and connecting code, then checks stage connections and model, container, and prompt choices against supplied specifications.

中文简介正在准备中。当前显示英语简介。

• Create a workflow that runs augmentation without full auto-labeling
• Combine detection and captioning into a custom processing chain
• Check model, container, and prompt choices against an external spec

Run a Kubernetes workflow that changes clothing in cropped person images, searches person attributes, and builds augmented datasets. The skill handles input preparation, run monitoring, and result retrieval for person re-identification data work.

中文简介正在准备中。当前显示英语简介。

• Create clothing variations from cropped person images
• Prepare augmented datasets for person re-identification
• Search person attributes and inspect generated captions

Audit and prepare a GPU Kubernetes cluster for PAIDF Orchestration. Check available GPU capacity, deploy the Airflow workflow controller, choose external or in-cluster model services, and report whether the environment is ready for workflow execution.

中文简介正在准备中。当前显示英语简介。

• Checking a new GPU cluster before running workflows
• Deploying the Airflow controller
• Choosing external or in-cluster model services