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 sep41-token-safetygit 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/sep41-token-safety)<a href="https://agentmods.dev/skills/plamentsv/plamen/sep41-token-safety"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/sep41-token-safety/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/sep41-token-safety"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/sep41-token-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 17 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.02312 |
| Opus 5 | $0.00020 | $0.01156 |
| Sonnet 5 | $0.00008 | $0.00462 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
sep41-token-safety 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 7d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEP41_TOKEN_SAFETY Skill (Soroban)
Trigger Pattern: SEP-41 token patterns detected (
approve/transfer/transfer_from/allowance/balance) Inject Into: Breadth agents, depth-token-flow, depth-edge-case Finding prefix:[ST-N]Rules referenced: R4, R5, R10, R11, R13, R15
SEP-41 is Soroban's token interface standard, analogous to ERC-20. It introduces Soroban-specific behaviors that differ from ERC-20: allowances use Temporary storage with expiration_ledger, the approve function can be front-run similarly to ERC-20, and the Stellar Asset Contract (SAC) bridges Stellar classic assets into Soroban with additional accounting complexity.
1. Approve Race Condition
The approve(from, spender, amount, expiration_ledger) function overwrites the current allowance without checking the existing value. This is the ERC-20 approve race condition, present identically in SEP-41:
| Token Contract | approve Guarded? |
Guard Type | Effective? |
|---|---|---|---|
{contract} |
YES/NO | require!(current == 0) / none |
YES/NO |
Attack sequence:
- Owner approves spender for 100 tokens
- Owner submits new approval for 50 tokens
- Spender front-runs the new approval and spends the 100-token allowance
- New 50-token approval is set
- Spender spends 50 more tokens — net: 150 tokens spent, 50 intended
Soroban-specific note: Soroban does not have a traditional mempool — transaction ordering is determined by validators, not fee-based priority. However, multi-operation transactions and DEX routing can create ordering dependencies. The race condition is lower likelihood than on EVM but the vulnerability exists.
Check for:
- Does
approveallow setting non-zero over non-zero without an intermediate zero-set step? - Does the protocol documentation warn users about the race condition?
- Are there any off-chain tools (like
increaseAllowance/decreaseAllowanceequivalents) to safely adjust allowances?
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.
- 7d ago First seen · 147 lines · 41 tokens per session scan A 03416e966a09
sep41-token-safety is a skill published in the GitHub repository PlamenTSV/plamen (295 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 2,312 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 2026-09-03.
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.
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.
web3-grep-arsenal
Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific vulnerability classes.