菜单
Review network segmentation and firewall/ACL design for security: zone separation, ruleset hygiene, lateral-movement containment, and zero-trust / microsegmentation. Use to assess or design network architecture defensively (not active testing).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Statically review a Claude Code / AI-agent setup for security misconfigurations — risky hooks, over-broad permissions, untrusted or cleartext MCP servers, hardcoded secrets, endpoint redirection, over-privileged agents/skills, and prompt-injection in steering files. Use when asked to audit a `.claude/` directory, `settings.json`, `.mcp.json`, a plugin/marketplace, or `CLAUDE.md`, or to add a config-security gate to CI. Drives the `agentscanner` CLI.
Review the training / MLOps pipeline for security weaknesses — data-poisoning surface, feature-store and data-source trust, experiment-tracking and model-registry access control, secrets, and reproducibility/provenance. Use when assessing how models are built and promoted, not how they're served or consumed.
Review the provenance and integrity of models, datasets, and ML artifacts pulled from hubs/registries — unsafe deserialization (pickle, PyTorch/Keras/joblib), untrusted model sources, model/dataset tampering, and signing. Use when an app loads third-party model weights or datasets, or before promoting a model.
Harden a deployed model inference endpoint — authn/authz, rate limiting and abuse control, input validation, and exposure to model-extraction / inversion / membership-inference attacks. Use when reviewing how a model is served (REST/gRPC, Triton/TorchServe/KServe, or a hosted inference API), not how it was trained.
Export a finished security artifact (report, executive summary, diagram, spreadsheet of findings) to Google Drive — right folder, clear naming, and shareable with the intended audience. Use when a deliverable needs to be handed to stakeholders who live in Drive/Docs/Sheets rather than a wiki or tracker.
Turn a security finding (vuln, pentest issue, review item) into a well-formed Jira issue — mapped severity→priority, remediation/repro in the body, labels and components set, and dedup-checked against existing issues. Use when findings need to become tracked, assignable work in Jira.
| name | network-segmentation-review |
| description | Review network segmentation and firewall/ACL design for security: zone separation, ruleset hygiene, lateral-movement containment, and zero-trust / microsegmentation. Use to assess or design network architecture defensively (not active testing). |
An assessment of how well the network limits blast radius: are zones separated, are firewall rules least-privilege, and is lateral movement contained — with prioritized fixes.
any/any), unused/shadowed
rules, stale entries, missing egress filtering, default-allow.A review: zone/rule · issue · severity · fix, plus a target segmentation design and
egress policy. Visualize zones with security-diagramming:architecture-diagram;
report with security-reporting.
Flat networks are the force-multiplier behind most breaches — containing east-west
movement limits blast radius more than almost any other network control. Hunt broad
(any/any) and stale firewall rules; default-deny egress is commonly missing and
high-value. Pairs with network-pentest (which demonstrates the lateral paths).