离线环境下的本地安全审查与加固建议
Scanned 9/2/2026
Install to Claude Code
npx -y skills add wangzhe04/ruyi-workbench-oss --skill security-guidance --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Security Guidance?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wangzhe04-security-guidance)More formats (shields.io, HTML) on the badges page.
---
name: 安全加固
description: 离线环境下的本地安全审查与加固建议
---
# Security Guidance
Use this skill for local security review and hardening in an offline environment.
Workflow:
1. Run `code_review_scan` and `dependency_inventory` for quick signals.
2. Inspect matching code before treating a signal as a finding.
3. Prioritize exploitable issues: secrets, injection, unsafe shell execution, XSS, broad CORS, disabled TLS, unsafe file writes, and permission boundaries.
4. Recommend patches that work without cloud scanners or package downloads.
5. Separate confirmed findings from hardening suggestions.
Output expectations:
- Include file and line references for confirmed issues.
- Explain impact and the minimal fix.
- Mention scanners or dependency advisories that could not run because the environment is offline.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...