Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-iam-diagnosegit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-iam-diagnose)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-iam-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-iam-diagnose/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-iam-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-iam-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00266 | $0.02910 |
| Opus 5.5 | $0.00106 | $0.01164 |
| Sonnet 5.5 | $0.00053 | $0.00582 |
| Haiku 4.5 | $0.00027 | $0.00291 |
Grade A, and why
huawei-cloud-iam-diagnose scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud IAM Reference Permission Analysis (IAM 参考性权限分析)
Overview
This skill performs reference permission analysis for Huawei Cloud IAM. It answers questions
like "does user <u> have permission to do <action> on resource <r>?" by expanding the user's
permission chains and statically evaluating policy documents.
Honest Capability Boundary (read first)
| Capability | Status | Notes |
|---|---|---|
| User-level permission simulation (AWS IAM Policy Simulator equivalent) | ❌ Not available | Neither the IAM CLI nor the SDK provide a SimulatePrincipal API |
| Group-level check | ✅ | keystone_check_project_permission_for_group, keystone_check_domain_permission_for_group, keystone_checkrole_for_group |
| Agency-level check | ✅ | check_project_permission_for_agency, check_domain_permission_for_agency, check_all_projects_permission_for_agency |
| Check whether a user is in a group | ✅ | keystone_check_user_in_group |
| Policy document fetch | ✅ | get_policy_version_v5, keystone_show_permission, show_custom_policy |
| Authorization schema metadata | ✅ | get_authorization_schema_v5 |
Therefore this skill outputs a "大概率有权限/无权限" (likely has / likely has not) reference verdict — it is NOT an authoritative authentication result. When 100% certainty is required, guide the user to the IAM console, an actual API trial call, or CTS audit logs (see references/verification-method.md).
Architecture
User input: user (+ maybe target action/resource)
↓
1. Resolve user_id (v3 keystone by name → fallback v5 full scan)
↓
2. Expand permission chains
├─ User direct policies (v5 ListAttachedUserPoliciesV5)
├─ User's groups (v3 keystone_list_groups_for_user)
│ ├─ group attached policies (v5 ListAttachedGroupPoliciesV5)
│ └─ group roles: domain / all-projects (v3)
└─ Agencies (v5 ListAgenciesV5 + attached policies/roles)
↓
3. Fetch policy documents (get_policy_version_v5 / role.policy)
↓
4. Evaluate Allow/Deny per policy doc + grade confidence
↓
5. Emit verdict + precision grade + chain trace (+ real check cross-validation)
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/acceptance-criteria.md 2.3 KB
- references/cli-installation-guide.md 954 B
- references/dataflow-diagram.md 1.7 KB
- references/iam-policies.md 2.6 KB
- references/verification-method.md 3.1 KB
- requirements.txt 54 B
- scripts/check_agency_permission.py 3.8 KB runs code
- scripts/check_env.ps1 2.6 KB runs code
- scripts/check_env.sh 3.2 KB runs code
- scripts/check_group_permission.py 5.3 KB runs code
- scripts/config.py 4.1 KB runs code
- scripts/diagnose_user_permission.py 16 KB runs code
- scripts/ensure_cli.sh 1.8 KB runs code
- scripts/ensure_env.py 17 KB runs code
- scripts/iam_common.py 15 KB runs code
- scripts/install_cli.sh 1.4 KB runs code
- scripts/list_attached_group_policies.py 1.1 KB runs code
- scripts/list_attached_user_policies.py 1.5 KB runs code
- scripts/list_iam_agencies.py 869 B runs code
- scripts/list_user_groups.py 2.3 KB runs code
- scripts/trace_permission_chain.py 7.6 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 20d ago Changed · -3 lines f8f80498a42a
- 29d ago First seen · 257 lines · 266 tokens per session scan A d59863c97330
huawei-cloud-iam-diagnose is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 266 tokens to every session and 2,910 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.
Other skills, from other repositories
auditing-gcp-iam-permissions
Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI, Policy Analyzer, and IAM Recommender.
performing-aws-privilege-escalation-assessment
Performing authorized privilege escalation assessments in AWS environments to identify IAM misconfigurations that allow users or roles to elevate their permissions using Pacu, CloudFox, Principal Mapper, and manual IAM policy analysis techniques.
securing-aws-lambda-execution-roles
Securing AWS Lambda execution roles by implementing least-privilege IAM policies, applying permission boundaries, restricting resource-based policies, using IAM Access Analyzer to validate permissions, and enforcing role scoping through SCPs.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
performing-cloud-native-threat-hunting-with-aws-detective
Hunt for threats in AWS environments using Detective behavior graphs, entity investigation timelines, GuardDuty finding correlation, and automated entity profiling across IAM users, EC2 instances, and IP addresses.
detecting-aws-iam-privilege-escalation
Detect AWS IAM privilege escalation paths using boto3 and Cloudsplaining policy analysis to identify overly permissive policies, dangerous permission combinations, and least-privilege violations.