Security risk review
Skill ligyDt/ai-ide-init-template/trae/.agents/skills/security-risk-review
面向 Codex、Cursor、CodeBuddy、TRAE 的中文 AI IDE 项目初始化模板，内置多角色协作、Skills、MCP、Hooks 与安全验证。
npx -y skills add ligyDt/ai-ide-init-template --skill security-risk-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
审查凭据、隐私、外部访问、账号、支付、真实数据、发布和生产操作风险。用于高风险动作之前。
SKILL.md
0.5 KB, 115 tokens by cl100k_base, as published. Nobody here has run it
安全风险审查
识别资产、数据类别、信任边界、主体、环境和权限，检查凭据保存、最小权限、审计、脱敏、撤销和保留机制。真实数据、生产读写、支付和不可逆远端动作均需明确批准。输出风险、控制要求与阻断结论。
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most review quality skills give in 115 tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07
- Ask questions one at a timein 81 of 1048, across 64 files
- Provide a recommended answer for each questionin 73 of 1048, across 50 files
- Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
- Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
- Interview the user relentlessly about the planin 38 of 1048, across 13 files
- Order findings by severityin 31 of 1048
- Resolve each branch of the decision treein 27 of 1048, across 5 files
- Run a grilling sessionin 26 of 1048, across 5 files
- Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
- Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
- Create documentation files lazilyin 24 of 1048, across 5 files
- Assign severity to every findingin 24 of 1048
Said here and by no other author read
- identify subjects, environments, and permissions
- check credential storage mechanisms
- verify auditing mechanisms
- verify data desensitization mechanisms
- verify revocation mechanisms
- verify retention mechanisms
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.