What is cairo-auditor?

A security review workflow for Cairo code, the programming language used for Starknet smart contracts.

Use it to audit a Cairo/Starknet repository, run deeper adversarial checks, or review selected contract files.

It searches for contract security problems and combines findings into one structured report.

cairo-auditor — Skill for Claude Code and Codex by keep-starknet-stran

Install

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.

Any agent

npx skills add keep-starknet-strange/starknet-agentic --skill cairo-auditor

Clone the repo

git clone --depth 1 https://github.com/keep-starknet-strange/starknet-agentic

Made for: Claude Code, Codex.

Or install cairo-auditor, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/keep-starknet-strange/starknet-agentic/cairo-auditor/github.svg)](https://agentmods.dev/skills/keep-starknet-strange/starknet-agentic/cairo-auditor)

Your own site

<a href="https://agentmods.dev/skills/keep-starknet-strange/starknet-agentic/cairo-auditor"><img src="https://agentmods.dev/badge/skills/keep-starknet-strange/starknet-agentic/cairo-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/keep-starknet-strange/starknet-agentic/cairo-auditor"><img src="https://agentmods.dev/badge/skills/keep-starknet-strange/starknet-agentic/cairo-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,786 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 5 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 System Prompt Leakage · line 450
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
medium Data Exfiltration · line 106
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 153
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 160
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 173
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.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.06786
Opus 5	$0.00023	$0.03393
Sonnet 5	$0.00009	$0.01357
Haiku 4.5	$0.00005	$0.00679

Measured 10d ago against content hash 220d4e18c4ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cairo-auditor scanned grade A with 2 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 10d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/doctor.sh, scripts/quality/audit_local_repo.py, scripts/quality/deep_integrity.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

- Otherwise create one with `mktemp -d "${TMPDIR:-/tmp}/cairo-auditor.XXXXXX"` and `chmod 700`.

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.

- `command -v curl` must succeed, and

skills/cairo-auditor/SKILL.md · 460 lines

How it starts

The opening of the file, as written. The whole thing — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cairo/Starknet Security Audit

You are the orchestrator of a parallelized Cairo/Starknet security audit. Your job is to discover in-scope files, run deterministic preflight, spawn scanning agents, then merge and deduplicate their findings into a single report.

Quick Start

Default flow: workflows/default.md
Deep flow: workflows/deep.md
Structured findings: references/structured-findings.md
Report schema: references/report-formatting.md

Starknet.js Examples

import { Account, Contract, RpcProvider } from "starknet";

const provider = new RpcProvider({ nodeUrl: process.env.STARKNET_RPC! });
const account = new Account({ provider, address: process.env.ACCOUNT_ADDRESS!, signer: process.env.PRIVATE_KEY! });
const contract = new Contract({ abi, address: process.env.CONTRACT_ADDRESS!, providerOrAccount: account });

try {
  // View call for quick sanity checks while triaging findings.
  const owner = await contract.call("owner", []);

  // State-changing probe used during exploit-path validation.
  const tx = await contract.invoke("set_owner", [owner]);
  const receipt = await provider.waitForTransaction(tx.transaction_hash);
  console.log({ finality: receipt.finality_status });
} catch (err) {
  console.error("audit probe failed", err);
}

Error Codes and Recovery

Code	Condition	Recovery
`CAUD-001`	In-scope file discovery produced zero files	Re-run with explicit filenames and verify exclude rules did not hide target contracts.
`CAUD-002`	Preflight scan failed or unavailable	Run `python3 "{skill_root}/scripts/quality/audit_local_repo.py"` manually and attach output to the audit context.
`CAUD-003`	Agent bundle generation failed	Rebuild `{workdir}/cairo-audit-agent-*-bundle.md` and confirm each bundle has non-zero line count.
`CAUD-004`	Conflicting findings across agents	Keep the highest-confidence root cause, then request a focused re-run on the disputed file.
`CAUD-005`	Report includes only low-confidence items	Re-run deep mode with the host-specific cairo-auditor entrypoint (for example, `/starknet-agentic-skills:cairo-auditor deep` in Claude Code) and add deterministic checks from Semgrep/audit findings.
`CAUD-006`	Deep mode requested but specialist agents unavailable	Re-run in an environment with Agent tool support. Where fail-closed enforcement is enabled, `--allow-degraded` explicitly permits fallback.
`CAUD-007`	Deep mode host capability preflight failed	For hosts with preflight enforcement enabled, surface remediation and stop before findings unless `--allow-degraded` is explicitly present.
`CAUD-008`	Agent transport instability or stalled specialist completion	Retry failed/stalled specialists once. In hosts with deep-mode enforcement enabled, unresolved specialist outages are treated as fail-closed unless explicitly degraded.
`CAUD-009`	Strict-model requirement could not be satisfied	Re-run on a host that supports required models, or omit `--strict-models` to allow documented fallback.

Read the full file on GitHub · 460 lines

Files

What ships with it

60 files 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.

Changes

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.

10d ago First seen · 460 lines · 47 tokens per session scan A 220d4e18c4ae

Subscribe to this mod's changes

cairo-auditor is a skill published in the GitHub repository keep-starknet-strange/starknet-agentic (80 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 6,786 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Security Web3 and blockchain agentic-framework audit cairo chatgpt claude codex moltbook semgrep starknet vulnerabilities

cairo-auditor

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Asks for rootlowPrivilege escalation

Makes network callslowCapability

How it starts

Cairo/Starknet Security Audit

Quick Start

Starknet.js Examples

Error Codes and Recovery

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

Cairo — StarkNet Smart Contract Reference

evm

hyperliquid

solana

analyzing-ethereum-smart-contract-vulnerabilities

mpp-agent