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 UnboundCompute/security-agent-skills --skill reviewing-secrets-manager-access-policy-trustgit clone --depth 1 https://github.com/UnboundCompute/security-agent-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/unboundcompute/security-agent-skills/reviewing-secrets-manager-access-policy-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/reviewing-secrets-manager-access-policy-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/reviewing-secrets-manager-access-policy-trust/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/unboundcompute/security-agent-skills/reviewing-secrets-manager-access-policy-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/reviewing-secrets-manager-access-policy-trust.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 | $0.00170 | $0.01844 |
| Opus 5.5 | $0.00068 | $0.00738 |
| Sonnet 5.5 | $0.00034 | $0.00369 |
| Haiku 4.5 | $0.00017 | $0.00184 |
Grade A, and why
reviewing-secrets-manager-access-policy-trust 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing secrets-manager access-policy trust: who can actually read the secret
A managed secrets store is only as strong as the policy that decides who reads each secret, and that decision is rarely written in one place. The effective read set is the union of the secret's resource policy, the identity policies of every principal in the account, and the permission to decrypt the key that protects the secret. A secret can look locked down on its resource policy while a broad identity policy elsewhere grants read on every secret, or while a wide key-decrypt grant lets a principal decrypt what the store would otherwise deny. Wildcards on secret names or paths quietly sweep in unrelated secrets. You review these by computing who the combined policy actually admits and comparing that to the secret's intended consumers.
When to use
- Applications fetch secrets from a managed secrets manager or a vault-style store.
- Access is governed by a combination of resource policy, identity policy, and key-decrypt permission.
- Secret names or paths are matched by wildcard in any policy that grants read.
Scope check
Review secret access only in accounts and stores you own or are authorized to assess. Confirming a read retrieves a real secret value, so stay inside the authorized store and treat any retrieved value as sensitive within scope, never exfiltrating it. If you can't name the authorization, stop.
The loop
-
Establish the secret's intended consumers first. For each secret, name the principals that legitimately need to read it: the specific service role, the specific workload. This is the false-positive killer: a policy admitting exactly those consumers is correct however powerful the store is. Name the consumers, then compute the actual read set against them.
-
Read the resource policy for who it admits. The secret's own policy grants read to named principals or patterns. Determine the true set it admits, noting any broad principal (an account, a wildcard) and any condition that is meant to scope it. This is one term of the union, not the whole answer.
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.
- 1mo ago First seen · 129 lines · 170 tokens per session scan A 70d82e711433
reviewing-secrets-manager-access-policy-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 170 tokens to every session and 1,844 once invoked, about $0.0007 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 2026-09-05.
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…
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…
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…
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…
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. 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…
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"…