agentleFS
orlando-vazquez-careerorlando-vazquez-career/astra-protocol/.agents/skills/astra-audit/SKILL.md

astra-audit

Skill2 starsChanged 2 months agoMITView on GitHub

Fase 5 de ASTRA (Auditoria). Recorre el checklist de seguridad universal y el de la familia de cadena (Soroban, EVM, L2, Syscoin) sobre el codigo, la Carta y el registro de testnet; escribe docs/astra/audit.md con hallazgos, severidad, estado y veredicto. Usar cuando el usuario dice "auditar", "revision de seguridad del contrato", "que puede salir mal", "audit" o antes de cualquier mainnet.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No editar código ni tests (solo lectura).

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- GENERADO por astra skills sync desde skills/astra-audit/SKILL.md — no editar a mano; editar el canonico y re-correr el sync -->

astra-audit — Fase 5: Auditoría

Cuándo

Con la entrada testnet registrada. Produce docs/astra/audit.md con veredicto: apto o no-apto. La corre un rol distinto del que construyó (A9): otra familia de modelos si se puede; si no, se declara.

Pasos

  1. Lee docs/astra/chart.md, el código, los tests, .astra/deployments.json (commit de la entrada testnet), docs/astra/orbit.md (amenazas) y guides/audit-checklist.md completa.
  2. Recorre el checklist universal: control de acceso, reentrancy, aritmética, entradas, oráculos, front-running, upgradeabilidad, pausas, eventos, dependencias, secretos.
  3. Recorre la sección de la familia: Stellar (TTL, require_auth, recursos, SEP-0041, activos clásicos, upgrade), EVM (tx.origin, delegatecall, aprobaciones, receive, gas, EIP-712), Layer 2 (secuenciador, retiros, paymasters) y Syscoin (bloques lentos, puentes, PoDA).
  4. Cruza la interfaz desplegada en testnet con la Carta: toda función pública que no esté en la Carta es hallazgo alta. Cada invariante sin test de propiedad es hallazgo.
  5. astra check sobre el commit auditado; un error de secretos es hallazgo crítica.
  6. Escribe docs/astra/audit.md desde templates/audit.template.md: auditor y familia, commit, tabla | ID | Severidad | Estado | Hallazgo | Fix | con función y línea, riesgos aceptados (los acepta la persona), lo que no se pudo verificar.
  7. Veredicto: apto solo sin críticas ni altas abiertas. Si hay, no-apto, y el sprint vuelve a astra-build; después de los fixes, re-prueba en testnet y vuelve a auditar.
  8. Confirma con astra check --gate mainnet que auditoria-apta quede en OK.

No hacer

  • No editar código ni tests (solo lectura). No cerrar hallazgos propios. No aceptar riesgos por cuenta del agente.

Done

audit.md completo, fechado, con veredicto; auditoria-apta OK si es apto.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.