「destructive-action」の検索結果

Classify every destructive/gated action an agent body can attempt (git, filesystem, network, shell, github) into block/approve/allow tiers, and audit whether the pre-tool and post-tool governance backing that classification is real: blocked actions proven zero-side-effect by a negative fixture, every denial backed by a receipt and a transcript event, every block-tier denial paired with a safe alternative, and no unmanaged or same-UID body ever marked "contained." Use when building or reviewing Agent Harbor's C5 governance gate (destructive git blocker, approval request/result, denial receipts), gating a new tool surface before it can run destructive commands, or auditing whether an existing "destructive-action blocked" claim actually has evidence behind it. NOT for proving an existing sandbox boundary actually contains an adversary once an action is isolated (use sandboxed-adversarial-test-harness), deciding where in a DAG to place a human review node or designing the approval UX itself (use human-gate-designer), or designing the general work-receipt schema across an entire agent task (use agent-work-receipt-designer).

日本語の概要は準備中です。原文の説明を表示しています。

Scaffold a custom AI agent harness via `metaharness new {name} --template {id} --host {id}`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.

日本語の概要は準備中です。原文の説明を表示しています。

[omh] Agent or automation safety risks: review prompt, tool, secret, dependency, destructive-action, and explicit local plugin risks before agent or code execution. Use when the user says: security-safety-review, security safety review, ai coding safety, agent safety review, prompt injection review, tool permission review, secret exposure review, destructive action review.

日本語の概要は準備中です。原文の説明を表示しています。

[omh] Folder cleanup, renames, or deletions: policy overlay for local file tasks - add path scoping and destructive-action gates after preferring native file tools for ordinary list, search, organize, copy, move, and rename actions. Use when the user says: workspace-file-operator, workspace file operator, file operator, file operation, file operations, filesystem task, filesystem operation, file system task.

日本語の概要は準備中です。原文の説明を表示しています。

Establish least privilege, credential rotation, webhook authenticity, signed-URL custody, log minimization, and destructive-action controls. Use when designing or hardening Adobe integrations. Trigger with "secure Adobe integration", "rotate Adobe secret", or "verify Adobe webhook".

日本語の概要は準備中です。原文の説明を表示しています。

Research-grounded workflow for designing, reviewing, and improving video game user interfaces, including HUDs, menus, navigation, focus states, onboarding/tutorials, objective tracking, input prompts, readability, accessibility, and destructive-action flows. Use when asked how to make good game UI, critique a game UI or HUD, propose UI/UX guidelines, design menu or gameplay interfaces, compare HUD vs diegetic/spatial presentation, create a UI design brief, or run a usability/accessibility review for PC, console, mobile, or VR games.

日本語の概要は準備中です。原文の説明を表示しています。

Implement GNOME's 4-tier destructive-action pattern: undo toasts instead of confirmation dialogs, AdwAlertDialog for irreversible actions. Use when adding delete, remove, clear, or other destructive actions.

日本語の概要は準備中です。原文の説明を表示しています。