openai/codex-security

attack-path-analysis

Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/openai/codex-security --skill attack-path-analysis

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Security Attack Path Analysis

Determine whether each supplied finding has a supported attacker path, what impact it has, and whether it is reportable. Before creating or retaining files, read ../../references/artifact-storage.md.

Establish the attack path

For a scan phase, use its per-scan threat model and candidate set from ../../references/scan-artifacts.md. Preserve supplied input paths. If a required scan artifact is unavailable, report the missing input.

For standalone analysis, use the supplied finding, repository, threat model or security policy, and context. A per-scan artifact is not required. State material assumptions and ask for missing context only when it prevents a meaningful assessment.

  1. Establish the in-scope attacker, affected product surface, entry point, controlled input, security boundary, and sensitive operation. Trace the path from repository evidence.
  2. Identify relevant controls and the strongest counterevidence. Explain what they establish, which prerequisites remain, and whether the exact claimed boundary is crossed.
  3. Assess impact and likelihood from those facts, then apply references/severity-policy.md. Keep facts, severity calibration, and the final policy decision distinguishable in the result.
  4. Return an explicit decision for every eligible candidate, including ignored or deferred candidates. Do not replace a supported instance with a neighboring finding or lose its root-control location.

Use repository evidence and explicitly supplied context. Access the network only when the user has expressly authorized it; an offline scan never accesses the network. Do not invent unsupported attack chains. Missing deployment or public-ingress evidence can limit confidence without defeating an otherwise supported finding.

Scan integration

Standard scans and Deep Scan workers assess attack paths within their ordinary Standard scan workflow; neither invokes this separate phase skill.

Compact Workbench Diff

When a workbench-backed $security-diff-scan has a scanId:

  • Load the per-scan threat model and all validated candidates with list_codex_security_candidates({ scanId, cursor?, limit? }).
  • Analyze every reportable or deferred validation candidate. Preserve candidate identity and existing discovery and validation fields.
  • Submit every decision together with record_candidate_attack_paths({ scanId, attackPaths: [{ candidateId, attackPath }] }). Submit attackPaths: [] when no candidate enters this phase. The tool preserves the stored candidate order.
  • These nested decisions are the complete phase output. Do not create duplicate reports, receipts, or manual ledgers.

Other phase-based scans

Use the active workflow's report and receipt paths in ../../references/scan-artifacts.md. Every candidate entering this phase must have an explicit decision and a receipt with its ID, facts or exact proof gap, and report reference. Record ignored candidates before excluding them from the surviving finding set.

For repository-wide or scoped-path scans, include validation closure rows marked reportable or survives: yes, even if discovery did not assign a polished finding number. Preserve affected entrypoint/wrapper, root-control, sink, and concrete-implementation locations supplied by validation.

Output

For standalone analysis, follow the caller's format or return a concise assessment per finding. Scan phases use their output contract above. Include:

  • title and supplied candidate, instance, and ledger identities;
  • precise affected locations and attacker-to-impact steps;
  • relevant facts from references/attack-path-facts.md;
  • controls, counterevidence, prerequisites, and material proof gaps;
  • impact, likelihood, calibrated severity, and final policy decision with their reasons.

Retain enough evidence to explain both surviving and suppressed findings. Apply the severity policy to the established facts rather than reopening discovery or substituting a different attack story.