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 PlamenTSV/plamen --skill account-abstraction-securitygit clone --depth 1 https://github.com/PlamenTSV/plamenWrote 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/plamentsv/plamen/account-abstraction-security)<a href="https://agentmods.dev/skills/plamentsv/plamen/account-abstraction-security"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/account-abstraction-security/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/plamentsv/plamen/account-abstraction-security"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/account-abstraction-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 124 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00043 | $0.01741 |
| Opus 5 | $0.00022 | $0.00870 |
| Sonnet 5 | $0.00009 | $0.00348 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
account-abstraction-security 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 9d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injectable Skill: Account Abstraction Security
Protocol Type Trigger:
account_abstraction(detected when ERC-4337 interfaces, EntryPoint, UserOperation, or Paymaster patterns found) Inject Into: Breadth agents, depth-external Language: EVM only (other VMs handle account abstraction natively without smart contract validation stacks) Finding prefix:[AA-N]
Orchestrator Decomposition Guide
When decomposing this skill into depth agent investigation questions, map sections to domains:
- Section 1: depth-external (validation flow, external calls to EntryPoint)
- Section 2: depth-edge-case (paymaster edge cases, gas bounds)
- Section 3: depth-state-trace (signature validation state, module registry)
- Section 4: depth-token-flow (fee payment flows, token approvals)
When This Skill Activates
Recon detects ERC-4337 patterns: UserOperation, IAccount, IPaymaster, EntryPoint, validateUserOp, validatePaymasterUserOp, postOp, isValidSignature (ERC-1271), or smart account/wallet factory patterns.
1. UserOperation Validation Flow
For each validateUserOp implementation:
1a. Signature Verification
- What signature scheme is used? (ECDSA, multi-sig, passkey/WebAuthn, session keys)
- Is the signature verified against the CORRECT signer(s)?
- Is the
userOpHashcomputed correctly (includeschainId,entryPoint,nonce)? - Can a valid signature for one operation be replayed for a different operation? (nonce management)
1b. Nonce Management
- Is the nonce scheme sequential, 2D (key + sequence), or custom?
- Can nonce be skipped or reused?
- For 2D nonces: can different keys interfere with each other?
- Does the nonce validation happen BEFORE or AFTER signature verification?
1c. Return Value Correctness
validateUserOpmust returnvalidationDataencoding(authorizer, validUntil, validAfter).- Does the return value correctly encode time bounds?
- Does returning
0(success) vs1(failure) vs packed data follow the spec? - Can the function return success for an INVALID operation?
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.
- 9d ago First seen · 145 lines · 43 tokens per session scan A 4c1afe7c356f
account-abstraction-security is a skill published in the GitHub repository PlamenTSV/plamen (294 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,741 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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.
prowler-tour
Keeps product-tour definitions aligned with the UI features they describe. Trigger: When modifying UI components that have associated tours, editing tour definition files, or renaming data-tour-id attributes.
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.
evm-bytecode-analysis
Analyze supplied deployed EVM runtime bytecode with EVMole or guide a separate application in integrating a published EVMole Rust, Go, Python, or JavaScript binding. Use for unverified-contract inspection, ABI reconstruction from runtime code, selector discovery, storage-access analysis, EVM control-flow inspection…
talos-action-development
Develop, modify, review, and maintain standalone Talos actions in contracts/tasks/actions, including chain guardrails, contract bindings, transaction safety, schedules, action catalogues, and Talos documentation. Use when adding an action, changing an action’s behavior or parameters, updating a Talos schedule, or…
web3-poc-foundry
Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.