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 MangroveTechnologies/mangrove-agent --skill audit-securitygit clone --depth 1 https://github.com/MangroveTechnologies/mangrove-agentWrote 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/mangrovetechnologies/mangrove-agent/audit-security)<a href="https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/audit-security"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/audit-security.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.01387 |
| Opus 5 | $0.00065 | $0.00694 |
| Sonnet 5 | $0.00026 | $0.00277 |
| Haiku 4.5 | $0.00013 | $0.00139 |
Grade A, and why
audit-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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit — mangrove-agent trading bot
Read-only audit against the mangrove-agent repo. Covers:
- Wallet + signing surfaces (post-2026-04-24 incident focus)
- Web3 / crypto-specific threats (EIP-7702 delegation, permit abuse, tx replay, router allowlist drift, private-key lifetime, Fernet at rest)
- MCP tool layer (auth tier assignments, tool input validation, response leakage)
- OWASP Top 10 + CWE/SANS Top 25 (SQL injection via SQLite, SSRF via webhook URLs, path traversal via config files, etc.)
- Dependency CVEs (
pip-audit/safety checkagainstserver/requirements.txt) - Infrastructure (hook registration, docker-compose exposure, default API key shipping)
Process
-
Check for prior audits at
docs/audits/*-security-audit.md. If a recent one exists, read it to avoid re-flagging fixed issues and to track remediation. -
Wallet + signing invariants (CRITICAL — given 2026-04-24). Verify:
server/src/services/wallet_manager.py::_validate_sign_targetstill refuses: tx type 3, tx type 4,authorizationListfield, non-1inchto, non-1inch-spender approves, bare tx (noto)._ONEINCH_ROUTERSset matches known 1inch V5 + V6 addresses.sign_message()still raises unconditionally — no EIP-191 personal_sign path.- No other code path in
server/src/callsAccount.from_key,Account.from_mnemonic,sign_transaction,sign_message,sign_typed_data,sign_authorization, orsetCodeoutside ofwallet_manager.py. - Fernet
decrypt()is only called fromwallet_manager._load_secretandreveal_wallet_secret. reveal_wallet_secretresponse stays on the localhost REST endpoint, never exposed via MCP.
-
Hook-enforcement gaps. For each hook in
.claude/hooks/*.sh:- Confirm it's registered in
.claude/settings.jsonunder the right matcher. - Confirm it
set -uo pipefail, handles malformed JSON without crashing, and uses proper exit codes (0 = allow, 2 = block). - Confirm it doesn't log or exfiltrate secrets in its stderr message (particularly
block-wallet-secrets.sh).
- Confirm it's registered in
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 · 97 lines · 130 tokens per session scan A f0f4f2373b7d
audit-security is a skill published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 1,387 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
sui-publish
Publishing, upgrading, and deploying Sui Move packages. Use this skill when the user needs to publish a package, upgrade a published package, deploy to multiple networks, serialize transactions for multisig signing, run a local Sui network (localnet), prepare for Mainnet launch, monitor production deployments, or…
t2000-job
Escrow USDC for agent-to-agent deliverable work (A2A jobs). Use when hiring another agent for async work (research reports, builds, SLA tasks) or when selling deliverable work yourself (list a service: fixed price + SLA, no server needed), or posting/claiming open jobs on the board (t2 job open / claim) — anything…
t2000-setup
Set up a t2000 terminal Agent Wallet (t2 init) when the user needs a local CLI key file — not for Claude-only marketplace (that is Passport Connect OAuth only). Also use when they say "set up t2000", "install the wallet", or "connect t2000 to Claude / Cursor" if a local wallet is in scope. Covers npm CLI install…
sui-object-model
Deep reference for the Sui object model: ownership types, object abilities, dynamic fields, collections, versioning, transfer patterns, and derived objects. Use this skill whenever the user asks about Sui objects, object ownership (address-owned, shared, immutable, wrapped), how to transfer or share or freeze objects…
modern-move-syntax
Use when writing Move code on Sui to ensure 2024 edition syntax is used. Applies to method calls, string literals, vector operations, option handling, loops, and struct unpacking. Use whenever writing Move code to avoid legacy function-call syntax patterns.
composable-move-functions
Use when writing Move functions on Sui, especially public APIs. Applies to function visibility (public vs entry), parameter ordering, and return patterns. Use whenever designing function signatures or deciding whether functions should transfer objects or return them.