auditing-cross-account-role-trust-boundaries

auditing-cross-account-role-trust-boundaries is a skill for Claude Code from UnboundCompute/security-agent-skills. It costs 173 tokens per session (1,957 once invoked), scanned A, original, MIT.

A security review of cross-account IAM role trust policies. These policies control which users, services, or outside organizations may assume a cloud role and receive its permissions.

In plain words
What is it for?
Use it to review roles assumed by other cloud accounts, partner organizations, vendors, or other roles, and to trace where each permitted caller can go next.
Why use it?
It finds trust rules that admit too many callers, omit a required external ID, enable a confused-deputy attack, or create an unsafe chain from a weaker role to a stronger one.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the security-agent-skills plugin — 194 skills shipped together

Good fit Use it to review roles assumed by other cloud accounts, partner organizations, vendors, or other roles, and to trace where each permitted caller can go next.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unboundcompute/security-agent-skills/auditing-cross-account-role-trust-boundaries
Install

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.

Any agent
npx skills add UnboundCompute/security-agent-skills --skill auditing-cross-account-role-trust-boundaries
Clone the repo
git clone --depth 1 https://github.com/UnboundCompute/security-agent-skills

Made for: Claude Code.

Or install security-agent-skills, the plugin that ships this one along with the rest of its 194 skills.

Wrote 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.

agentmods badge for auditing-cross-account-role-trust-boundaries

README.md
[![agentmods](https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-cross-account-role-trust-boundaries/github.svg)](https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-cross-account-role-trust-boundaries)
Your own site
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-cross-account-role-trust-boundaries"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-cross-account-role-trust-boundaries/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.

agentmods 80×15 button for auditing-cross-account-role-trust-boundaries

Your own site · 80×15
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-cross-account-role-trust-boundaries"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-cross-account-role-trust-boundaries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,957 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00173 $0.01957
Opus 5 $0.00086 $0.00979
Sonnet 5 $0.00035 $0.00391
Haiku 4.5 $0.00017 $0.00196

Measured 12d ago against content hash 53c6392d7c6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

auditing-cross-account-role-trust-boundaries 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 12d 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.

skills/auditing-cross-account-role-trust-boundaries/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditing cross-account role trust boundaries: when the trust policy lets the wrong caller in

A role's trust policy decides who may assume it, and in a multi-account or partner setup that policy is the whole boundary between organizations. It fails in quiet ways. A principal element written as a wildcard, or as an entire account rather than a specific role, lets any identity in that account assume the role. A third-party integration role that omits or does not verify an external ID is open to the confused-deputy attack, where the vendor is tricked into assuming your role on an attacker's behalf. And assumption chains, where one role assumes another, can carry a low-privilege origin into high-privilege territory the trust policies never meant to connect. You audit these by reading each trust policy for who it actually admits and by following where an admitted principal can go next.

When to use

  • Roles in one account can be assumed from another account, a partner organization, or a third-party vendor.
  • A trust policy uses a broad principal, or a third-party role relies on an external ID for scoping.
  • One assumed role can assume another, forming a chain that may reach privileges the origin should not.

Scope check

Test role assumption only in accounts and organizations you own or are authorized to assess. A confirming assumption obtains real credentials in the target account, so stay inside the authorized accounts and never assume a role belonging to an organization outside your engagement. If you can't name the authorization, stop.

The loop

  1. Establish the intended trust relationship first. For each cross-account role, name who is supposed to assume it and why: which specific partner role, which service, which internal account. This is the false-positive killer: a trust policy that admits exactly the intended principal under the intended conditions is correct even in a sprawling multi-account setup. Name the intended relationship, then read the policy against it.

Read the full file on GitHub · 137 lines

Changes

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.

  1. 12d ago First seen · 137 lines · 173 tokens per session scan A 53c6392d7c6d

Subscribe to this mod's changes

auditing-cross-account-role-trust-boundaries is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 173 tokens to every session and 1,957 once invoked, about $0.0009 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

cloud-security-engineer

Cloud Security Engineer role bundle for cloud security posture management, IaC review, container security, and identity governance across AWS, Azure, and GCP. Orchestrates cloud-specific posture reviews and zero trust program assessments. Auto-invoked when the user needs help with cloud security configuration, IaC…

UnitOneAI/SecuritySkills · 79 tokens

azure-review

Performs an Azure security posture review against the CIS Microsoft Azure Foundations Benchmark v2.1.0. Auto-invoked when reviewing Azure infrastructure, Entra ID configurations, NSG rules, Defender for Cloud settings, or Key Vault access policies. Walks through all nine benchmark sections, evaluates each…

UnitOneAI/SecuritySkills · 81 tokens

gcp-review

Performs a GCP security posture review against the CIS Google Cloud Platform Foundation Benchmark v2.0.0. Auto-invoked when reviewing GCP infrastructure, IAM bindings, VPC firewall rules, Cloud Audit Logs, or GCS bucket security. Walks through all seven benchmark sections, evaluates each recommendation, and produces a…

UnitOneAI/SecuritySkills · 83 tokens

aws-review

Performs an AWS security posture review against the CIS Amazon Web Services Foundations Benchmark v3.0.0. Auto-invoked when reviewing AWS infrastructure, IAM policies, S3 configurations, CloudTrail settings, VPC security groups, or RDS encryption. Walks through all five benchmark sections, evaluates each…

UnitOneAI/SecuritySkills · 83 tokens

cloud-pivot-finder

Maps cloud infrastructure from domains and identifies pivot paths from external to cloud internals. Detects cloud providers, enumerates S3/GCS/Azure storage, finds subdomain takeover opportunities, discovers serverless functions, CI/CD exposure, and IaC leaks. Use when user asks for "cloud security", "S3 enumeration"…

Orizon-eu/claude-code-pentest · 104 tokens

prodcheck-review

Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…

FarzamHabibi/pre-production-checklist · 70 tokens