360 Secure SkillHub
360 安全技能中心

Security Scanner Triage

面向技能与自动化产物的安全扫描发现分诊 Skill：把扫描文本拆成离散结论，按数据流向、凭据、默认配置、文档不一致、权限与持久化分组，逐条对照代码与文档核验并标注确认程度，再给出严重性评级、影响范围与利用难度，以及最小补丁顺序和复扫清单。

okikesolutions
okikesolutions
热度 45.88
最近更新 2026-05-11 17:39:43
分类：安全依赖：读写文件 / 内部调用大模型应用场景：代码审查 / 报告撰写

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add security-scanner-triage
Metadata
name
security-scanner-triage
description
Triage security/virus scanner findings for skills and automations. Use when scanner reports mixed-risk findings (defaults, credential handling, data routing, metadata mismatch, docs inconsistency). Do not use for live incident response requiring SOC tooling. Success = prioritized true issues, false positives called out, and concrete remediation patch plan.

Security Scanner Triage

Workflow

  1. Normalize findings
  • Convert scanner text into discrete claims.
  • Group by category: data routing, credentials, defaults, docs mismatch, privilege/persistence.
  1. Verify against code/docs
  • Locate exact file/line evidence.
  • Mark each claim as:
    • Confirmed
    • Partially confirmed
    • Not reproducible
  1. Risk rate
  • Critical / High / Medium / Low
  • Include blast radius and exploitability notes.
  1. Remediation plan
  • Provide minimal patch order:
    1. safety first
    2. behavior/docs consistency
    3. version bump and publish notes
  1. Verification
  • Provide re-scan checklist and expected clean-state signals.

Output format

Use references/output-template.md.

Guardrails

  • Never leak secrets from .env.
  • Distinguish trust/disclosure issues from active vulnerabilities.
  • Always separate "data-routing transparency" findings from "security-impact" findings.