“injection”的搜索结果

用TypeScript实现claude-flow v3核心模块，按任务、会话等职责划分领域，梳理组件依赖，并实现SQLite存储、事件通知及单元与集成测试。

• 实现claude-flow v3基础模块
• 实现任务分配和状态管理
• 通过依赖注入连接SQLite

用TypeScript实现claude-flow v3核心模块，按任务、会话等职责划分领域，梳理组件依赖，并实现SQLite存储、事件通知及单元与集成测试。

• 实现claude-flow v3基础模块
• 实现任务分配和状态管理
• 通过依赖注入连接SQLite

Plan security controls for LLM applications and AI agents, covering malicious instructions, data leakage, model tampering, and API access. Includes guidance and code examples for filtering outputs, enforcing permissions, isolating networks, and recording audit events.

中文简介正在准备中。当前显示英语简介。

• Reviewing defenses against prompt injection in AI agents
• Filtering personal information from LLM responses
• Designing authentication and rate limits for LLM APIs

Test how agent workflows recover from repeatable simulated failures, including tool timeouts, worker restarts, and lost memory. Produces a fault matrix, event timeline, and verdict showing whether state, safety boundaries, and retry budgets were preserved.

中文简介正在准备中。当前显示英语简介。

• Test recovery from MCP or tool timeouts
• Verify checkpoint recovery after a worker restart
• Check outcomes when one parallel branch fails

Review MCP configurations for exposed credentials, risky command patterns, and package versions that can change unexpectedly. Produce a report with severity levels and suggested fixes without running the commands defined in the configuration.

中文简介正在准备中。当前显示英语简介。

• Reviewing .mcp.json before committing changes
• Checking a new MCP server before adoption
• Finding hardcoded credentials in configurations

Review and improve .NET/C# code against project conventions. Cover public API documentation, dependency injection for supplying services to classes, asynchronous operations, tests, configuration, logging, and input validation, including guidance for Semantic Kernel integrations.

中文简介正在准备中。当前显示英语简介。

• Review C# code against project conventions
• Improve XML documentation for public APIs
• Review asynchronous operations and dependency injection

Investigate process hollowing, where malicious code replaces a legitimate process in memory. Compare memory with disk files, examine process relationships, and correlate network activity to document suspicious processes and guide containment.

中文简介正在准备中。当前显示英语简介。

• Investigating process injection alerts from EDR
• Examining suspicious behavior in legitimate Windows processes
• Finding threats that run in memory

Build detections for fileless attacks on Windows using process activity, script logs, and endpoint monitoring. Investigate suspicious PowerShell, code injected into running processes, WMI persistence, and registry-based execution with logging guidance and detection query examples.

中文简介正在准备中。当前显示英语简介。

• Building detections for suspicious PowerShell activity
• Hunting for code injection into running processes
• Monitoring WMI persistence and registry-based execution

Analyze RAM dumps with Volatility 3 to investigate suspicious processes, network connections, injected code, and credential theft. Guides memory capture and evidence extraction, then organizes findings into a forensic report for incident response.

中文简介正在准备中。当前显示英语简介。

• Investigating malware that runs only in memory
• Checking suspicious processes and network connections
• Investigating signs of credential theft

Analyze access logs from AWS API Gateway, Kong, and Nginx with pandas, a Python data analysis library. Examine resource access patterns, authentication failures, and suspicious requests to investigate API abuse and inform detection rules.

中文简介正在准备中。当前显示英语简介。

• Investigating sequential access to resource IDs
• Examining spikes in authentication failures
• Checking for rate limit bypass and injection attempts

Analyze Cobalt Strike communication profiles and Beacon payload configurations to extract request paths, headers, timing, and process injection settings. Turn these indicators into a JSON report and network detection rules for Suricata or Snort.

中文简介正在准备中。当前显示英语简介。

• Analyzing a captured Malleable C2 profile
• Extracting communication settings from a Beacon payload
• Creating Suricata or Snort detection rules

Guides Python agent development with PydanticAI, covering tool calls and structured outputs checked against defined data types. Explains service injection, provider switching, streaming responses, and tests that run without calling a real language model.

中文简介正在准备中。当前显示英语简介。

• Building agents that return validated structured data
• Connecting customer support agents to order data
• Testing agent logic without real model calls

Review security across web apps, APIs, mobile apps, Kubernetes, and AI agents using six OWASP references. Identify risky authentication, access controls, configurations, and prompt handling, then use examples and checklists to plan fixes.

中文简介正在准备中。当前显示英语简介。

• Review login flows and access controls
• Check API authorization and data exposure
• Review mobile app storage and communications

Enable NanoClaw agents to deploy web applications to Vercel. The skill installs the Vercel CLI, a command-line tool, and configures automatic credential injection through OneCLI, supporting production deployment and deployment status checks.

中文简介正在准备中。当前显示英语简介。

• Enabling Vercel deployment for NanoClaw agents
• Configuring Vercel credentials through OneCLI
• Adding deployment tools to existing agent groups

Integrate Zoom Virtual Agent into an iOS app using WKWebView, an embedded web browser. Covers Swift and Objective-C configuration injection, messages exchanged with web content, support handoff handling, and rules for opening links.

中文简介正在准备中。当前显示英语简介。

• Embedding Zoom Virtual Agent in an iOS app
• Injecting configuration and registering message handlers
• Handling support handoff messages

Review code changes for security, performance, correctness, and maintainability. Get findings tied to files and lines, severity ratings, practical suggestions with code examples, and a recommendation to approve, request changes, or discuss further.

中文简介正在准备中。当前显示英语简介。

• Reviewing a pull request before merging
• Checking authentication and injection risks
• Finding excessive database queries and resource leaks

Review part designs for sheet metal, CNC machining, or injection molding. Compare geometry measurements with applicable supplier or tooling limits, then document manufacturing concerns, suggested changes, and checks that still need evidence.

中文简介正在准备中。当前显示英语简介。

• Review sheet metal bends and flat patterns
• Check CNC tool access and internal corners
• Review molding draft and undercuts

Manage the KubeSphere ServiceMesh extension built on Istio, Kiali, and Jaeger. Install or remove it, check deployment status, and investigate problems with staged releases, proxy injection, service topology, traffic metrics, and tracing across application components.

中文简介正在准备中。当前显示英语简介。

• Installing, upgrading, or removing ServiceMesh
• Investigating staged release routing problems
• Checking missing Istio proxy containers

Use Meta's Prompt Guard to detect malicious instructions in user prompts and external data. This skill guides input filtering, batch checks for retrieved documents, detection threshold adjustments, and splitting long text for inspection.

中文简介正在准备中。当前显示英语简介。

• Detecting attempts to override an LLM's instructions
• Checking API responses for embedded malicious instructions
• Batch screening documents retrieved for RAG

Review code or changes for exposed secrets, injection risks, weak encryption, and missing permission checks. Produce a structured report with severity, location, recommendations, and confidence, with a separate reviewer checking findings for false positives.

中文简介正在准备中。当前显示英语简介。

• Reviewing a module for security issues
• Checking changes for exposed secrets
• Preparing a vulnerability report with evidence

Review code changes for security, performance, correctness, and maintainability. Get findings tied to files and lines, severity ratings, practical suggestions with code examples, and a recommendation to approve, request changes, or discuss further.

中文简介正在准备中。当前显示英语简介。

• Reviewing a pull request before merging
• Checking authentication and injection risks
• Finding excessive database queries and resource leaks

Test REST, gRPC, and WebSocket APIs for weaknesses in authentication, access controls, input handling, and configuration. Provides protocol-specific checks, tool guidance, and detection indicators to help document reproducible findings and severity during authorized assessments.

中文简介正在准备中。当前显示英语简介。

• Check access controls across users and roles
• Review token lifecycles and request limits
• Assess gRPC and WebSocket security

Assess JWT authentication in web and mobile apps using a structured security checklist. Examine token signatures, key handling, validation, and storage to investigate authentication bypass risks and identify relevant fixes.

中文简介正在准备中。当前显示英语简介。

• Assessing JWT authentication in a web app
• Checking signature and key validation
• Reviewing token storage in mobile apps

Assess GraphQL APIs during penetration tests, from finding endpoints and mapping data structures to checking access controls, query limits, subscriptions, and uploads. Includes example queries, guidance for testing tools, and defensive controls for interpreting findings.

中文简介正在准备中。当前显示英语简介。

• Map GraphQL endpoints and data structures
• Check access controls across users and roles
• Review query limits and subscription security