OpenParable
Skip to content
← Back to skills

Analyze Codescan

DevOps & Security
analyze-codescan

Analyze Codescan is an Agent Skill for devops & security published in the ModelEngine-Group/fit-framework repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

分析 Code Scanning (CodeQL) 告警，评估安全风险并创建修复任务。当用户要求分析 Code Scanning 告警、CodeQL 告警时触发。参数为告警编号。

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/ModelEngine-Group/fit-framework/blob/HEAD/.agents/skills/analyze-codescan/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/analyze-codescan, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

分析 Code Scanning 告警

分析指定的 Code Scanning（CodeQL）告警，评估安全风险并创建修复任务。

执行步骤

  1. 获取告警信息:

    gh api repos/{owner}/{repo}/code-scanning/alerts/<alert-number>

    提取: rule (id/severity/description), tool (name), most_recent_instance (location/message)

  2. 创建任务目录和文件，基于 .agents/templates/task.md 模板。

  3. 定位和分析源码:

    • 根据 most_recent_instance.location 定位源码文件和行号
    • 读取告警所在的源码上下文
    • 理解 CodeQL 规则的含义和检测逻辑
    • 检查是否有其他位置也存在相同问题

  4. 评估安全风险（代码路径可达性、可利用性、影响程度）。

  5. 输出分析文档到 analysis.md。

  6. 更新任务状态。

  7. 提示下一步: plan-task 设计修复方案，或 close-codescan 关闭告警。

注意: Critical/High 级别立即处理，Medium 计划处理，Low 可延后。