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 trilwu/secskills --skill exploiting-web3-smart-contractsgit clone --depth 1 https://github.com/trilwu/secskillsWrote 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/trilwu/secskills/exploiting-web3-smart-contracts)<a href="https://agentmods.dev/skills/trilwu/secskills/exploiting-web3-smart-contracts"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/exploiting-web3-smart-contracts/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/trilwu/secskills/exploiting-web3-smart-contracts"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/exploiting-web3-smart-contracts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, 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 Tool Misuse · line 59 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Supply Chain · line 66 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Tool Misuse · line 66 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Privilege Escalation · line 59 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 60 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 59 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Data Exfiltration · line 379 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 382 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00047 | $0.02925 |
| Opus 5 | $0.00023 | $0.01463 |
| Sonnet 5 | $0.00009 | $0.00585 |
| Haiku 4.5 | $0.00005 | $0.00293 |
Grade B, and why
exploiting-web3-smart-contracts scanned grade B with 3 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 5d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
curl -fsSL https://deb.nodesource.com/setup_18.x | sudo -E bash - Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -L https://foundry.paradigm.xyz | bash Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://deb.nodesource.com/setup_18.x | sudo -E bash - How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploiting Web3 and Smart Contracts
When to Use
- Smart contract security auditing
- DeFi protocol testing
- Web3 application pentesting
- Blockchain vulnerability assessment
- NFT platform security
Scope and authorization. A deployed mainnet contract is not a test target. It is a live system custodying other people's funds, it is permissionless — so nothing stops you technically — and it is irreversible once you transact. None of that makes exploitation authorized.
- Fork, never touch mainnet. Prove every finding against a local fork (Anvil, Hardhat, Tenderly) or a testnet deployment. There is no legitimate reason to run a working exploit against a live contract.
- The law here is unsettled — which is a reason for caution, not comfort. Two headline prosecutions went the exploiter's way: a Paris court acquitted the Platypus Finance pair in December 2023, holding that calling a public smart contract was not unauthorized access and that the emergency-withdrawal manipulation did not meet the fraud standard; and in May 2025 a US judge vacated Avraham Eisenberg's Mango Markets convictions on venue and insufficient evidence of misrepresentation, a ruling prosecutors have appealed. Do not read those as permission. Both turned on jurisdiction- specific facts, the Platypus court expressly left civil liability open, and in every one of these matters the defendant was arrested, had funds seized, and litigated for years before prevailing. Winning eventually is not the same as being authorized.
- Bug bounty scope is narrow and literal. Immunefi-style programs typically require proof on a fork, forbid mainnet exploitation and live-user impact, and have specific disclosure channels. Read the scope for the specific program before testing, not after.
- Unaudited ≠ abandoned. An anonymous or inactive deployer does not make a contract ownerless; the depositors are still identifiable victims.
For contracts you do not own, work from source and simulation only, and disclose through the project's published channel or a coordinating platform.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 474 lines · 47 tokens per session scan B d3975b3fd286
exploiting-web3-smart-contracts is a skill published in the GitHub repository trilwu/secskills (137 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 2,925 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hyperliquid-reader
Read Hyperliquid (app.hyperliquid.xyz) perp + spot market data via opencli (read-only, public info API). Use whenever the user wants Hyperliquid perpetual or spot markets, mark/oracle/mid prices, 24h change, funding rates (hourly or annualized APR), open interest, volume, the L2 order book, OHLCV candles, historical…
grayscale-crypto-sectors
Use when evaluating crypto through a Grayscale-style Crypto Sectors lens: sector taxonomy, FTSE/Grayscale index eligibility, fee/usage fundamentals, sector-share valuation, ETP/trust wrappers, and Zcash-style privacy-as-money theses.
ansem-crypto
Use when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style crypto market framework.
a16z-crypto
Use when evaluating crypto networks and companies through an a16z crypto lens: web3 adoption, infrastructure vs apps, open networks, and long-duration crypto ecosystem investing.
arthur-hayes-liquidity
Use when evaluating crypto markets through an Arthur Hayes-style liquidity lens: dollar liquidity, funding, risk appetite, cycle psychology, and macro-driven crypto positioning.
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.