What is security-authz-and-trust-boundaries?

Guidance for checking whether the current user is allowed to access or change a particular resource. It covers permissions, ownership, roles, and separation between customers or organizations.

Use it when implementing server-side access checks, ownership rules, role permissions, tenant isolation, or authorization for reads and writes.

It prevents treating login as proof of permission or trusting identifiers supplied by the user, which can expose another person’s or tenant’s data.

security-authz-and-trust-boundaries — Skill by andrewsrigom

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 andrewsrigom/agent-skills --skill security-authz-and-trust-boundaries

Clone the repo

git clone --depth 1 https://github.com/andrewsrigom/agent-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/security-authz-and-trust-boundaries/github.svg)](https://agentmods.dev/skills/andrewsrigom/agent-skills/security-authz-and-trust-boundaries)

Your own site

<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/security-authz-and-trust-boundaries"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/security-authz-and-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/security-authz-and-trust-boundaries"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/security-authz-and-trust-boundaries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 445 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00445
Opus 5.5	$0.00022	$0.00178
Sonnet 5.5	$0.00011	$0.00089
Haiku 4.5	$0.00006	$0.00044

Measured 2mo ago against content hash ffd9b09b9c6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security-authz-and-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 2mo 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.

security/security-authz-and-trust-boundaries/SKILL.md · 67 lines

What it actually says

Security Authz And Trust Boundaries

Use this skill when the main risk is unauthorized access caused by weak trust-boundary design.

Scope

authorization checks
ownership verification
role and permission design
tenant isolation
trusting user-controlled identifiers

Default path

Derive the actor from the trusted server-side auth context.
Define the resource and action being authorized.
Check authorization on the server for every privileged read and write.
Verify ownership, tenant membership, or explicit permission at the resource boundary.
Default to deny when the actor-resource relation is unclear.

When to deviate

Use coarse role checks only when resources are not user-scoped or tenant-scoped.
Cache authorization decisions only when invalidation and revocation are explicit.
Allow UI-based filtering for UX only if the server still enforces the same boundary.

Guardrails

Authentication is not authorization.
Resource identifiers from the client are not proof of access.
Role checks alone are often insufficient in multi-tenant or ownership-based apps.
Keep authorization close to the action, not only at route entry.

Avoid

checking permissions only in the UI
trusting userId, tenantId, or role values from request payloads
authorizing broad route access while skipping resource-level checks
default-allow behavior when actor-resource relationship is missing

Verification checklist

actor comes from trusted auth context
resource and action are explicit
authorization happens on the server
ownership or tenant checks are enforced where needed
default deny behavior is clear

Output Shape

When answering with this skill, prefer:

actor
resource
action
required trust boundary
missing or weak authorization check

References

Trust boundary checklist

Files

What ships with it

1 file 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/trust-boundary-checklist.md 526 B

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.

2mo ago First seen · 67 lines · 56 tokens per session scan A ffd9b09b9c6e

Subscribe to this mod's changes

security-authz-and-trust-boundaries is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 56 tokens to every session and 445 once invoked, about $0.0002 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 2026-08-31.