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-account-abstraction-and-paymaster-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-account-abstraction-and-paymaster-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-account-abstraction-and-paymaster-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-account-abstraction-and-paymaster-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-account-abstraction-and-paymaster-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-account-abstraction-and-paymaster-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 | $0.00188 | $0.02208 |
| Opus 5.5 | $0.00075 | $0.00883 |
| Sonnet 5.5 | $0.00038 | $0.00442 |
| Haiku 4.5 | $0.00019 | $0.00221 |
Grade A, and why
auditing-account-abstraction-and-paymaster-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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing account abstraction and paymaster trust: validation, payment, and execution are three trusts
In an ERC-4337 stack a user operation is validated by the smart account, paid for by a paymaster, bundled by a bundler, and executed through the entry point, and those are separate trust decisions made by separate parties. Each is a place trust can be misplaced. The account's validation decides whether a signature and nonce are acceptable; if it accepts what it should reject, an attacker executes operations as the account. The paymaster decides whether to sponsor an operation's gas; if it sponsors what it should not, an attacker drains its deposit by submitting operations that cost the paymaster and benefit no legitimate user, a denial-of-wallet on the sponsor. The entry point and bundler order and submit operations; if an operation can be replayed or reordered for gain, the lifecycle itself is the exploit. And validation runs under strict rules about what state it may read, mutable or external state in validation is both a denial vector and a soundness hole. The audit walks the user-operation lifecycle and checks each trust: what validation accepts, what the paymaster agrees to pay for, and what the ordering allows. You audit this by crafting user operations that probe each decision.
When to use
- An ERC-4337 account-abstraction stack validates, sponsors, and executes user operations across a smart account, a paymaster, a bundler, and the entry point.
- A paymaster sponsors gas and could be made to pay for operations it should not.
- Account validation may accept a bad signature or nonce, or read mutable or out-of-scope state.
Scope check
Test account-abstraction trust only against contracts and infrastructure you own or are authorized to assess, on a testnet or a local fork. Submitting user operations and probing a paymaster spends real gas and can drain a real deposit, so use test funds on a fork and never drain a live paymaster or execute against an account that is not yours. If you can't name the authorization, stop.
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 · 142 lines · 188 tokens per session scan A 9046ed8a204f
auditing-account-abstraction-and-paymaster-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 188 tokens to every session and 2,208 once invoked, about $0.0008 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
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…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
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-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…
linear-claude-skill
Manage Linear issues, projects, and teams.