菜单
Use this skill to review a PR or diff for security regressions. Do not use it for full-repository audits or legal contract review.
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
Use this skill to audit RAG and AI application security, including retrieval boundaries, prompt injection, citations, memory, and data exposure. Do not use it as a scanner or exploit runner.
Use this skill to audit backend authorization, IDOR, ownership checks, and tenant isolation. Do not use it for smart contracts or legal contract review.
Use this skill to audit CI/CD workflows, dependencies, build scripts, releases, artifacts, and package publishing. Do not use it for runtime application authz review.
Use this skill only when the user explicitly selects security finding IDs to fix. Do not use it to fix all findings or perform broad refactors.
Use this skill to convert a security incident or public vulnerability pattern into reusable audit prompts, checklists, tests, and AGENTS.md rules. Do not use it to generate exploit instructions.
Use this skill to audit LLM agents, tool calling, MCP integrations, prompt injection, data exfiltration, and tool permissions. Do not use it for ordinary backend authz unless agent/tooling is involved.
| name | pr-security-review |
| description | Use this skill to review a PR or diff for security regressions. Do not use it for full-repository audits or legal contract review. |
Review the current PR, diff, or changed-files summary for security regressions.
Default audit-only. Do not commit, push, merge, or edit files.
id: F-001
severity: Critical | High | Medium | Low | Informational
confidence: High | Medium | Low
category:
affected_code:
root_cause:
exploit_path:
preconditions:
impact:
evidence:
minimal_fix:
regression_test:
auto_fix_suitability: Safe | Needs Human Review | Do Not Auto-Fix
notes:
使用这个 skill 进行PR 安全审查。它应该帮助审查者把输入边界、风险证据、影响、修复建议和回归测试组织成可复核的安全输出。
适用于 已有 PR、diff 或 changed-files summary，需要判断安全回归、blocking issue 和 missing tests。如果请求超出这些边界，先说明范围差异，并选择更合适的 prompt、skill 或人工 review 路径。
不要用于完整仓库审计、智能合约协议深审、法律合同 review 或自动修复全部问题。不要把这个 skill 当作自动扫描整个仓库、执行 exploit、上传私有源码或 secrets、自动提交、自动推送或 auto-merge 的许可。
默认 audit-only。未经明确授权，不 patch、不 commit、不 push、不创建 PR、不 merge。不要执行 exploit，不要访问生产系统，不要打印 secrets。涉及 IAM、authz 模型、资金、治理、terminal 执行或 agent-tooling 权限的修复必须进入人工 review。
使用 canonical finding format。每个 finding 都要包含 severity、confidence、category、affected_code、root_cause、exploit_path、preconditions、impact、evidence、minimal_fix、regression_test、auto_fix_suitability 和 notes。