34 skills · sorted by relevance
Manages agent isolation levels and resource boundaries. Configures strict, moderate, and permissive isolation profiles. Activate on 'isolation level', 'agent isolation', 'resource boundaries', 'sandboxing', 'agent containment'. NOT for permission validation (use dag-permission-validator) or runtime enforcement (use dag-scope-enforcer).
The English summary is being prepared. Showing the original description.
Manages agent isolation levels and resource boundaries. Specifies concrete controls and the evidence needed to assess their boundaries. Activate on 'isolation level', 'agent isolation', 'resource boundaries', 'sandboxing', 'agent containment'. NOT for permission validation (use dag-permission-validator) or runtime enforcement (use dag-scope-enforcer).
The English summary is being prepared. Showing the original description.
Configure permission checks for unattended Antigravity CLI runs. The setup combines blocking rules, automatic approval for scoped operations, AI classification for ambiguous calls, and single-use approval tokens to control tool access within a verified workspace.
Analyze suspected malware through code inspection and behavior observed in an isolated environment. Extract indicators of compromise, such as suspicious domains and file paths, and create YARA file-matching rules or Sigma behavior-detection rules from the findings.
Configure email security gateways to detect targeted phishing messages. Set up sender impersonation protection, link checks, isolated attachment analysis, and custom rules, then validate quarantine actions and alerts for suspected attacks.
Investigate reported phishing emails by checking sender details, links, and attachments. Identify affected recipients and exposed login credentials, guide removal of malicious messages across the organization, and secure compromised accounts with password resets and session revocation.
Build AI agents that inspect screenshots, choose actions, and operate a mouse and keyboard. Covers the observation and action loop, desktop control examples, and isolated environments that restrict access to files, credentials, and networks.
Handle Git and GitHub CLI commands blocked by a sandbox, an environment that restricts access. Retry only authorized commands on the host, then check authentication, repository status, or pull request details there.
Run the pre-flight checklist before an agent drives a browser — the untrusted-web-content threat (every page is attacker-controllable), the credential and session-cookie exposure, the action-confirmation gates for purchases and posts, and the sandboxing that limits the damage. Use when asked let my agent browse safely, is it safe to give the agent computer/browser use, guardrails before the agent uses my browser, or review my browser agent's setup. Produces the sandbox decision, the content-injection defenses, the action gates, and the credential-isolation rules.
The English summary is being prepared. Showing the original description.
Use when building ANY macOS app — windows, menus, sandboxing, distribution, AppKit bridging or modernization (control events, state restoration, concentric corners), or macOS-specific SwiftUI patterns.
The English summary is being prepared. Showing the original description.
Audit an agent's harness against the four rings: containment, guides, sensors, permissions. Use when the user asks whether their agent setup is safe, wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails, or asks what a bad session could break. Read-only: reports the blast radius and a hardening list, changes nothing. Do NOT use for context layout (context-audit) or cost routing (gate-check).
The English summary is being prepared. Showing the original description.
Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior.
The English summary is being prepared. Showing the original description.
Expert guidance on macOS platform capabilities. Covers sandboxing, app extensions, menu bar apps, and background execution. Use when implementing system integration features.
The English summary is being prepared. Showing the original description.
Configure agy-auto PreToolUse security gate to run Antigravity CLI (agy) unattended with layered policy controls instead of --dangerously-skip-permissions.
The English summary is being prepared. Showing the original description.
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when "computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation, Claude computer, OpenAI Operator, browser agent, visual agent, RPA with AI, " mentioned.
The English summary is being prepared. Showing the original description.
Configure Claude Code permissions — tool approval rules, permission modes, managed policies, and sandboxing. Use when setting up permission rules, configuring allow/deny/ask policies, debugging permission prompts, deploying managed settings for organizations, or controlling Bash/Read/Edit/WebFetch/MCP/Agent tool access.
The English summary is being prepared. Showing the original description.
Use ArrowJS when a coding agent needs to add or maintain small reactive web interfaces using DOM-native JavaScript, template literals, SSR/hydration packages, and optional WASM sandboxing.
The English summary is being prepared. Showing the original description.
Use when building autonomous LLM agents operating in live environments. Protects against prompt injection, tool abuse, data exfiltration, and runaway loops. Keywords: guardrails, prompt injection, IPI, safety, sandboxing, NeMo, LLM Guard.
The English summary is being prepared. Showing the original description.
Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).
The English summary is being prepared. Showing the original description.
Claude Code workflow tips from Boris Cherny (creator of Claude Code) and the Claude Code team. Use when: setting up Claude Code, optimizing workflows, running parallel sessions, configuring CLAUDE.md, using skills/commands, subagents, hooks, MCP integrations, or learning best practices. Covers: git worktrees, plan mode, verification, permissions, Slack MCP, BigQuery, prompting tips, plugins, custom agents, sandboxing, keybindings, status lines, output styles, customization, /simplify for code quality, /batch for parallel code migrations, /loop for scheduled tasks, code review agents, /btw for mid-task questions, /effort max reasoning, remote control sessions, voice mode, setup scripts, session naming, /color, PostCompact hook, auto mode, /schedule cloud jobs, iMessage plugin, auto-memory, and auto-dream, mobile app, session teleporting, Cowork Dispatch, Chrome extension, Desktop app, /branch forking, --bare SDK startup, --add-dir multi-repo, --agent custom agents, /voice input.
The English summary is being prepared. Showing the original description.
Codex workflow tips from Boris Cherny and the Codex team. Use when setting up Codex or optimizing workflows: parallel sessions, worktrees, plan mode, AGENTS.md, skills, subagents, hooks, MCP, permissions, and sandboxing.
The English summary is being prepared. Showing the original description.
Construa agentes de IA que interagem com computadores como humanos fazem - visualizando telas, movimentando cursores, clicando botões e digitando texto. Cobre Computer Use da Anthropic, Operator/CUA da OpenAI e alternativas de código aberto. Foco crítico em sandboxing, segurança e tratamento dos desafios únicos do controle baseado em visão. Use quando: computer use, automação de desktop agent, controle de tela IA, agente baseado em visão, automação de GUI.
The English summary is being prepared. Showing the original description.
Use when building Hugging Face smolagents, code-executing agents, Python-action agents, Hub-shared tools, or lightweight agent prototypes that need sandboxing and provider flexibility.
The English summary is being prepared. Showing the original description.
Responds to phishing incidents by analyzing reported emails, extracting indicators, assessing credential compromise, quarantining malicious messages across the organization, and remediating affected accounts. Covers email header analysis, URL/attachment sandboxing, and mailbox-wide purge operations. Activates for requests involving phishing response, email incident, credential phishing, spear phishing investigation, or phishing remediation.
The English summary is being prepared. Showing the original description.