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 auditing-ansible-become-and-vault-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/auditing-ansible-become-and-vault-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ansible-become-and-vault-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ansible-become-and-vault-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/auditing-ansible-become-and-vault-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ansible-become-and-vault-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 | $0.00179 | $0.02179 |
| Opus 5 | $0.00089 | $0.01090 |
| Sonnet 5 | $0.00036 | $0.00436 |
| Haiku 4.5 | $0.00018 | $0.00218 |
Grade A, and why
auditing-ansible-become-and-vault-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 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing Ansible become and vault trust: when the control node runs as root everywhere
An agentless configuration tool is a fleet-wide root shell with a scheduler. The control node connects to every managed host and runs tasks that escalate privilege, and it decrypts the secrets those tasks need. Two trust questions decide the blast radius. First, escalation scope: become is often set at the play or role level so every task runs privileged, and any role, variable, or templated input that flows into those tasks runs as root on every host it touches. Second, secret handling: vault-encrypted values are only as protected as the decryption key, and a key exposed to the runner, passed on a command line, or logged is a fleet-wide secret leak. When a play escalates and decrypts across many hosts, an untrusted role or an exposed key is not one host's problem. You audit this by scoping where escalation applies and tracing what runs under it, and by checking how vault secrets are decrypted and whether the key or the plaintext leaks.
When to use
- Playbooks escalate privilege with become across managed hosts, often at the play or role level.
- Roles, collections, or variables come from shared or external sources and run under that escalation.
- Vault-encrypted secrets are decrypted on the control node, and the key or plaintext handling may leak.
Scope check
Audit playbooks and vault handling only for fleets and control nodes you own or are authorized to assess, on non-production hosts. Running a play escalates on real hosts and decrypts real secrets, so use a non- production inventory and never exfiltrate a decrypted secret. If you can't name the authorization, stop.
The loop
- Establish where escalation legitimately applies first. Name which tasks genuinely need privilege and on which hosts, versus where become is set broadly out of convenience. This is the false-positive killer: escalation scoped to the specific tasks that need it, running only first-party reviewed roles, is correct. Name the legitimate escalation, then find where it is broader.
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.
- 12d ago First seen · 140 lines · 179 tokens per session scan A e0ed27bf2dd7
auditing-ansible-become-and-vault-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 179 tokens to every session and 2,179 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.
Other skills, from other repositories
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…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
swiftui-expert-skill
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.