AGENT SKILL

iam-helper-for-policy-management

Streamlines the creation, modification, and management of IAM allow policies (v1) and deny policies (v2). Manages access control across Resource Manager resources (Organization, Folder, Project) and individual resources. Use when creating, updating, listing, or deleting IAM allow policies or deny policies. Don't use for access denial troubleshooting (use iam-helper-for-troubleshooting), temporary privileged access (use iam-helper-for-privileged-access-management), configuring VPC Service Controls, or managing network firewall rules.

License 许可
Apache-2.0
所属仓库
google/skills
最近更新
2026-11-14
Stars
★ 2.4w
Forks
2.0k

01 前言 Front Matter

name
iam-helper-for-policy-management
metadata
{ "version": "1.0.1", "category": "Security" }
description
Streamlines the creation, modification, and management of IAM allow policies (v1) and deny policies (v2). Manages access control across Resource Manager resources (Organization, Folder, Project) and individual resources. Use when creating, updating, listing, or deleting IAM allow policies or deny policies. Don't use for access denial troubleshooting (use iam-helper-for-troubleshooting), temporary privileged access (use iam-helper-for-privileged-access-management), configuring VPC Service Controls, or managing network firewall rules.

02 资源文件 3

03 SKILL.md 正文

IAM Helper for Policy Management

Orchestrates the lifecycle and management of IAM allow and deny policies across IAM v1 (allow policies) and IAM v2 (deny policies).

Usage Attribution

MUST READ: Before executing any gcloud, REST API, or MCP command, you MUST read and follow the instructions in Usage Attribution.


Core Concepts & Paradigms

IAM operates across two policy paradigms:

  1. IAM v1 (Allow Policies): Grants roles to principals (users, service accounts, groups, domains) on specific resources. Supports Resource Manager resources (organizations, folders, projects) as well as individual resources across supported Google Cloud services.
  2. IAM v2 (Deny Policies): Sets explicit organization-, folder-, or project-level guardrails that prevent specified principals from using designated permissions, regardless of any allow policies granted. Evaluated before allow policies.

Workflow & Decision Tree

When receiving a policy management request, determine whether the operation is Read-Only or Mutating, and whether it targets IAM v1 (Allow Policies) or IAM v2 (Deny Policies):

1. Read-Only Operations (Autonomous Execution)

Read-only actions include the following:

  • IAM v1 Allow Policies: get-iam-policy on project/folder/organization, or gcloud iam list-testable-permissions //cloudresourcemanager.googleapis.com/projects/PROJECT_ID.
  • IAM v2 Deny Policies: gcloud iam policies list or gcloud iam policies get with --attachment-point and --kind=denypolicies.

For read-only actions, execute the command autonomously to inspect state, and present the query results clearly to the user.

2. Mutating Operations (Plan & Confirm Protocol)

Mutating operations include the following:

  • IAM v1 Allow Policies: add-iam-policy-binding, remove-iam-policy-binding, or set-iam-policy across project, folder, organization, or resource levels (see references/v1-allow-policies.md).
  • IAM v2 Deny Policies: create, update, or delete deny policies on attachment points (cloudresourcemanager.googleapis.com/projects/PROJECT_ID, cloudresourcemanager.googleapis.com/folders/FOLDER_ID, or cloudresourcemanager.googleapis.com/organizations/ORG_ID) using YAML/JSON policy files (see references/v2-deny-policies.md).

For mutating operations, follow the Plan & Confirm Protocol below. DO NOT execute mutating commands autonomously without prior user approval.


Execution & Safety Protocol

  • Plan and Confirm (No Autonomous Mutation): Mutating allow and deny policy changes modify live security perimeters and access controls. You MUST NOT execute mutating gcloud commands directly via tool calls without explicit prior confirmation from the user. When asked to apply a mutating change, do the following:
    1. Formulate the Command: Generate the exact, fully constructed gcloud command (including all parameters such as --member, --role, --attachment-point, --kind=denypolicies, and --policy-file).
    2. Warn of Impact & Propagation: Issue a general warning that the change could impact access in a live environment and takes time to propagate across Google Cloud global infrastructure.
    3. Request User Confirmation: Prompt the user for approval before applying the changes to the live environment.
  • Post-Execution Verification: After the user approves and the mutating policy change is executed, run the corresponding verification command (see references/v1-allow-policies.md and references/v2-deny-policies.md for exact verification steps) to verify that the active state matches expectations before reporting completion.
  • Security Guardrail (Public & Blanket Access Refusal): Never grant allUsers or allAuthenticatedUsers basic roles (roles/owner, roles/editor, roles/viewer, roles/admin, roles/writer, and roles/reader) or broad permissions. Explicitly refuse blanket public access requests, explain the severe security risks of public project ownership/access, and propose scoped, least-privileged role bindings for specific authenticated identities instead.

Supporting Links

04 同仓库更多 Skills

google
google/skills

cloud-operator-share-context

Shares Google Cloud operating context the user or their team already have — environments, projects, services and regions, product preferences, best practices, architecture guidance, runbooks — found in agent instruction files, local memory, skills and workflows, and the repository's GCP docs, with the operator agent's memory after the user reviews the list. Use when the user runs this skill, accepts the cloud-operator or cloud-operator-setup skill's offer to share their existing Google Cloud context, or asks to share, import or save that context or a GCP fact for the operator agent. Don't use for ordinary GCP requests, which go to the cloud-operator skill.

★ 2.4w
google
google/skills

cloud-operator-setup

Sets up the operator agent in a Google Cloud project via the autocloud MCP server: picks the operator project, creates or checks the user's operator agent, saves the project, and offers to share the user's existing Google Cloud operating context with the operator agent's memory. Use when the user runs this skill, asks to set up the operator or create their operator agent, or chooses setup when the cloud-operator skill asks. Don't use for ordinary GCP requests or installing gcloud.

★ 2.4w
google
google/skills

developer-device-platform-device-run

Runs automated, non-interactive jobs on remote Android devices with Developer Device Platform (DDP) Device Run using `gcloud beta device-run sessions`: native Android executables or shell scripts (for example CLI tools, custom runners, test harnesses or benchmarks) and Android instrumentation tests, on one or many devices, then waits for completion and collects per-device outputs and logs. Use when running a binary or test suite on remote devices without an interactive connection. Don't use it for interactive device reservations, adb tunnels or screen streaming (use developer-device-platform-basics), or for local devices.

★ 2.4w
google
google/skills

compute-vm-creation

Guides the planning, configuration, and provisioning of standalone Google Compute Engine virtual machines (VMs) and bare metal (-metal) instances using gcloud CLI commands or direct MCP tool execution. Use ONLY when the user wants to create, configure, or provision a new standalone Compute Engine VM or bare metal instance from conversational intents (hardware sizing, region selection, OS image, networking, security defaults). DO NOT read or use for Google Kubernetes Engine (GKE) Autopilot or Standard clusters, Kubernetes node pools or Pods, container orchestration, managing existing VMs, Managed Instance Groups (MIGs), or Instance Templates.

★ 2.4w
google
google/skills

agent-platform-autorater-customization

Customizes an autorater (evaluation metric) for an AI agent so its grades match the user's own judgment, starting from the agent's real trajectories. Use when a user wants a metric tailored to their agent, wants to turn failing trajectories into rubrics, says an existing autorater grades their agent wrong, or wants an autorater to agree with human labels (autorater hillclimbing, judge calibration). Don't use for quick evals with built-in metrics or for improving the agent itself (use agent-platform-eval-flywheel).

★ 2.4w
google
google/skills

iap-agent-platform-troubleshooting

Diagnoses Identity-Aware Proxy (IAP) denials of outbound requests from Gemini Enterprise Agent Platform agents that run on Agent Runtime and send traffic through Agent Gateway. Use when an agent request fails with "Egress request is not authorized", when Cloud Audit Logs show an IAP egressViaIAP decision with granted false, when IAP audit entries are missing while debugging agent egress, or when Access policies, IAP allow policies, policy bindings, or Agent Registry entries might block agent egress. Don't use for Gemini model IAM permission errors (such as aiplatform.endpoints.predict), Agent Platform API errors, or Agent Runtime deployment or 500 errors (use agent-platform-troubleshooting instead). Don't use for setting up, creating, or connecting an Agent Gateway, or for IAP web apps, IAP TCP forwarding, or SSH.

★ 2.4w