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 hunting-iam-privilege-escalation-pathsgit 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/hunting-iam-privilege-escalation-paths)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-iam-privilege-escalation-paths"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-iam-privilege-escalation-paths/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/hunting-iam-privilege-escalation-paths"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-iam-privilege-escalation-paths.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 | $0.00144 | $0.01581 |
| Opus 5.5 | $0.00058 | $0.00632 |
| Sonnet 5.5 | $0.00029 | $0.00316 |
| Haiku 4.5 | $0.00014 | $0.00158 |
Grade A, and why
hunting-iam-privilege-escalation-paths 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting IAM privilege-escalation paths: a reachable chain to admin is the bug
Cloud access is a graph. Principals hold policies, policies grant permissions, and some of those permissions let a principal change the graph itself: pass a role, rewrite a policy, assume another identity. Privilege escalation is a path through that graph from where an attacker starts to a principal that can read the data or run the workloads that matter. No single permission looks alarming. The bug is the reachable chain, and you only see it when you follow the edges.
When to use
- You are reviewing cloud IAM: roles, policies, groups, and trust relationships.
- A principal is meant to be low-privileged and you want to prove it cannot reach admin.
- You have the policy documents and want to know what they compose into, not just what each says.
Scope check
Audit identity configuration in accounts you own or are authorized to test, with credentials provisioned for the review. If you can't name the authorization, stop.
The loop
-
Build the identity graph. Inventory every principal, the policies attached to it, the permissions those policies grant, and the resources they touch. Represent it as edges: principal grants permission on resource. The whole method is reachability over this graph, so the graph is the first artifact.
-
Enumerate the escalation primitives. Mark every permission that lets a principal change the graph rather than just use it: passing a more privileged role to a compute or automation service, creating or rewriting a policy version, attaching a policy to yourself, updating a function or task that already runs as a privileged role, or minting credentials for another identity. These edges are how one node reaches another's privilege.
-
Map trust relationships and their conditions. For each assumable identity, read who is allowed to assume it and under what condition. A trust that names a broad set of principals, a wildcard, or a condition that an attacker can satisfy is an edge into that identity. A precise trust condition is not.
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 · 130 lines · 144 tokens per session scan A d21c9e45eb6b
hunting-iam-privilege-escalation-paths is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 1,581 once invoked, about $0.0006 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"…