Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Awarexone/web3-bug-bounty-hunting-ai-skillsnpx agentmods add skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-solidity-audit-mcpWrote 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/awarexone/web3-bug-bounty-hunting-ai-skills/web3-solidity-audit-mcp)<a href="https://agentmods.dev/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-solidity-audit-mcp"><img src="https://agentmods.dev/badge/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-solidity-audit-mcp/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/awarexone/web3-bug-bounty-hunting-ai-skills/web3-solidity-audit-mcp"><img src="https://agentmods.dev/badge/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-solidity-audit-mcp.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 Supply Chain · line 38 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 42 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 Agent Snooping · line 53 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- medium MCP Rug Pull · line 46 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 79 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Data Exfiltration · line 286 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 Privilege Escalation · line 288 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.
- low Supply Chain · line 42 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.
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 | $0.00068 | $0.03251 |
| Opus 5 | $0.00034 | $0.01625 |
| Sonnet 5 | $0.00014 | $0.00650 |
| Haiku 4.5 | $0.00007 | $0.00325 |
Grade B, and why
web3-solidity-audit-mcp 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 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo install -m 755 /tmp/aderyn /usr/local/bin/aderyn 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 && foundryup 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 -L https://foundry.paradigm.xyz | bash && foundryup Copies of this mod
1 near-identical copy found in the catalogue:
- web3-solidity-audit-mcp — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL 36 — SOLIDITY AUDIT MCP: CLAUDE-NATIVE SMART CONTRACT SCANNER
From: github.com/mariano-aguero/solidity-audit-mcp — MCP server plugging Slither + Aderyn + SWC patterns into Claude Code 10 tools. 19 built-in finding explainers. 86 SWC detectors. DeFi + Web3 preset detector packs. CI/CD ready.
WHAT IT IS
An MCP server that gives Claude Code direct access to Slither, Aderyn, Slang AST, SWC pattern matching, and a gas optimizer — all in one unified pipeline with auto-deduplication. Instead of context-switching between tools, you ask Claude to audit a contract and get a merged, severity-sorted report.
Stack:
External (install separately):
Slither → Trail of Bits, 90+ detectors, deep data flow
Aderyn → Cyfrin Rust-based, fast AST analysis
Echidna → Property fuzzer (optional)
Halmos → Symbolic execution (optional)
Built-in (no install):
Slang → Nomic Foundation AST parser, precise pattern matching
SWC → 86 detectors against Smart Contract Weakness Classification registry
Gas → Storage packing, loop, calldata optimizations
INSTALL & CONFIGURE
# Prerequisites
pip install slither-analyzer solc-select
solc-select install 0.8.20 && solc-select use 0.8.20
curl -L https://foundry.paradigm.xyz | bash && foundryup
# Aderyn (Rust)
cargo install aderyn
# or: curl -L https://raw.githubusercontent.com/Cyfrin/aderyn/dev/cyfrinup/install | bash
# MCP server
npm install -g solidity-audit-mcp
# or: npx solidity-audit-mcp
# Optional fuzzers
brew install echidna # macOS
pip install halmos # symbolic execution
Wire into Claude Code — add to ~/.claude/mcp.json:
{
"mcpServers": {
"audit": {
"command": "npx",
"args": ["solidity-audit-mcp"]
}
}
}
Or project-level .mcp.json in repo root:
{
"mcpServers": {
"audit": {
"command": "node",
"args": ["/path/to/solidity-audit-mcp/dist/index.js"]
}
}
}
Docker (all tools pre-installed):
docker run -v $(pwd):/contracts solidity-audit-mcp audit /contracts/Token.sol
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 · 399 lines · 68 tokens per session scan B c83469306520
web3-solidity-audit-mcp is a skill published in the GitHub repository Awarexone/web3-bug-bounty-hunting-ai-skills (143 stars, last pushed 18d ago), licensed MIT. It adds 68 tokens to every session and 3,251 once invoked, about $0.0003 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 2026-08-30.
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.
propfund
Trade on PropFund, the decentralized on-chain prop firm for AI agents. Two layers: PropFund SCREENS you (a free evaluation, then a virtual "funded" probation leg that builds an immutable on-chain record — pool-as-counterparty, no real firm capital), and AgentDesk PAYS you (once your record clears the bar you graduate…
token-antiflash
When this skill is triggered, DO NOT directly implement all strategies. Follow this workflow.
solidity-coding
When a contract involves state initialization (external addresses, business parameters, role assignments), DO NOT default to any single approach. Follow this workflow.
solidity-checklist
Most on-chain operation failures come from skipping systematic verification. Instead of the reactive loop.
programmable-v4-hook-builder
Build, repair, validate, submit, or track a complete Programmable Uniswap v4 Custom launch through the public V3 API. Use when the user names Programmable and wants implementation or launch work for a hook, token, multi-contract graph, app, game, service, or hybrid. Do not use for explanation-only questions, unrelated…