Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

security-researcher

Estrelas3

Forks0

Atualizado28 de maio de 2026 às 15:57

Security audit and attack-surface decomposition. Use when Codex needs to review code changes, modules, dependencies, privileged operations, network boundaries, parsing, filesystem use, authn/authz, crypto, subprocesses, or supply chain risk.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

boris93

boris93/claude-setup

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Analistas de segurança da informaçãoInformática e Matemática·SOC 15-1212

Explorador de arquivos

2 arquivos

SKILL.md

readonly

name	security-researcher
description	Security audit and attack-surface decomposition. Use when Codex needs to review code changes, modules, dependencies, privileged operations, network boundaries, parsing, filesystem use, authn/authz, crypto, subprocesses, or supply chain risk.

Security Researcher

Source

Read ../../../roles/security-researcher.md before acting. That file is the canonical, model-neutral role definition and the source of truth for this skill.

Also read only the needed supporting files:

../../../contracts/finding.md
../../../contracts/scope-block.md
../../../policies/synthesis.md
../../../policies/scope-discipline.md
../../../policies/contract-enforcement.md
../../../vocabulary.md

If the relative paths are unavailable, try the same files under the configured Codex home ($CODEX_HOME when set, otherwise ~/.codex).

Procedure

Confirm the subsystem and attack surfaces in scope.
Decompose before auditing: privilege, network, data, supply chain, filesystem, auth, crypto, and process boundaries as applicable.
Trace concrete data flows from untrusted input to sensitive operations.
Report realistic vulnerabilities with exact locations and actionable fixes.
Keep speculative or out-of-scope concerns out of the main finding list.

Mais deste repositório

mesmo repositório

code-review-analyst

boris93/claude-setup

Scoped implementation-quality review. Use when Codex needs to review completed code changes for correctness, maintainability, codebase cohesion, edge cases, surface-level security, and architectural alignment. Use an RFC or plan as behavior context only; final RFC-to-code closure belongs to rfc-implementation-verifier.

2026-06-293

rfc-implementation-verifier

boris93/claude-setup

Final RFC-to-code closure review. Use after code review convergence when an implementation was based on an RFC or plan and Codex must verify the final reviewed code implements all required behavior, avoids extra behavior, and documents deviations before commit or PR.

2026-06-293

review-convergence-analyst

boris93/claude-setup

Review-loop convergence diagnosis. Use when repeated code review or gating findings suggest unresolved architecture, requirement, invariant, ownership, or abstraction problems rather than independent bugs.

2026-06-203

gating-review

boris93/claude-setup

Strict dirty-tree gating review. Use when Codex needs to review only the uncommitted changes in the current repository, investigate the surrounding code, and emit tightly qualified findings in the repository's gating-review JSON style.

2026-05-283

rfc-minimizer

boris93/claude-setup

Subtractive plan minimality review. Use after RFC or plan review convergence to identify non-load-bearing content, inflated site lists, premature abstraction, or defensive structure not justified by the stated scope or prior blocking findings.

2026-05-283

rfc-red-team

boris93/claude-setup

Adversarial technical plan stress testing. Use when Codex needs to break an RFC or plan by constructing concrete failure scenarios, temporal risks, compositional blind spots, and operator or user behavior that a standard review may miss.

2026-05-283

name	security-researcher
description	Security audit and attack-surface decomposition. Use when Codex needs to review code changes, modules, dependencies, privileged operations, network boundaries, parsing, filesystem use, authn/authz, crypto, subprocesses, or supply chain risk.

Security Researcher

Source

Read ../../../roles/security-researcher.md before acting. That file is the canonical, model-neutral role definition and the source of truth for this skill.

Also read only the needed supporting files:

../../../contracts/finding.md
../../../contracts/scope-block.md
../../../policies/synthesis.md
../../../policies/scope-discipline.md
../../../policies/contract-enforcement.md
../../../vocabulary.md

If the relative paths are unavailable, try the same files under the configured Codex home ($CODEX_HOME when set, otherwise ~/.codex).

Procedure

Confirm the subsystem and attack surfaces in scope.
Decompose before auditing: privilege, network, data, supply chain, filesystem, auth, crypto, and process boundaries as applicable.
Trace concrete data flows from untrusted input to sensitive operations.
Report realistic vulnerabilities with exact locations and actionable fixes.
Keep speculative or out-of-scope concerns out of the main finding list.