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 mtarcure/claude-vibe-squad --skill signature-validation-auditgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/signature-validation-audit)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/signature-validation-audit"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/signature-validation-audit/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/mtarcure/claude-vibe-squad/signature-validation-audit"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/signature-validation-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.00743 |
| Opus 5.5 | $0.00037 | $0.00297 |
| Sonnet 5.5 | $0.00019 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
signature-validation-audit 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 1mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Signature-Validation Audit (ECDSA fallback · precompile shadowing)
Audit signature-verification code for two 2025-26 auth-bypass classes that let an attacker forge a
"valid" signer: (a) ECDSA-fallback impersonation — a failed ecrecover/tryRecover (zero
address) silently falls back to an ERC-1271 contract check whose signer address is
attacker-influenced; and (b) precompile shadowing — using code.length == 0 as sole proof of an
EOA, so the 0x1–0x9 precompiles (zero code length, non-reverting) are treated as EOAs and shadow
the verification.
Source: corpus A §I.4 (Verichains / Sodium, July 2026, ~$270k — ECDSA fallback) and §I.5
(Verichains / Odos, Jan 2025, ~$50k — precompile shadowing).
Impact class: funds theft / auth bypass (intrinsic).
Governing method: Phase-3a hypothesis lane of systematic-attacking; emits leads only, held
to the identical verification spine.
Method
- Enumerate every signature entrypoint (
validateUserOp, permit paths, meta-tx relays, order settlement) withslither+ a customsemgreprule; map each to its recovery primitive. - ECDSA fallback: flag any path where
ecrecover/ECDSA.tryRecoverreturningaddress(0)(or a malformed-sig branch) does NOT hard-revert but instead routes to an ERC-1271 check. Verify the ERC-1271 signer is bound to an immutable, preconfigured owner, never a user-supplied payload field. - Precompile shadowing: flag any EOA/contract discrimination that relies on
extcodesize/code.length. Build aforgeboundary test that supplies precompile addresses0x01–0x09as the signer and asserts they are rejected. - PoC on
anvil --fork: supply an attacker contract (fallback case) or a precompile (shadowing case) as signer and drive an unauthorized approval/withdrawal; link-level negative control = a correctly-bound verifier rejects it. - Add
echidna/medusaproperties: "zero-address recovery never authorizes" and "signer code length is never the sole EOA proof."
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.
- 1mo ago First seen · 44 lines · 93 tokens per session scan A deebaa375342
signature-validation-audit is a skill published in the GitHub repository mtarcure/claude-vibe-squad (165 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 743 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
pay
Pay one external payment requirement within exact parent authority, through a payment method the payer holds, and read the paid resource back.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
document
Skill "document" from Hmbown/Codewhale, covering document, when to use, non-goals and workflow.