Agent SkillsTracer-Cloud/opensre › fixing-github-security-alerts

fixing-github-security-alerts

GitHub

修复 GitHub 安全及质量告警,支持 Dependabot、CodeQL 等。自动应用补丁或创建 PR,处理本地差异,不处理密钥扫描。

core/agent_harness/prompts/skills/fixing-github-security-alerts/SKILL.md Tracer-Cloud/opensre

Trigger Scenarios

用户请求修复 GitHub 安全或质量问题 提供 GitHub 安全/质量告警 URL

Install

npx skills add Tracer-Cloud/opensre --skill fixing-github-security-alerts -g -y
More Options

Non-standard path

npx skills add https://github.com/Tracer-Cloud/opensre/tree/main/core/agent_harness/prompts/skills/fixing-github-security-alerts -g -y

Use without installing

npx skills use Tracer-Cloud/opensre@fixing-github-security-alerts

指定 Agent (Claude Code)

npx skills add Tracer-Cloud/opensre --skill fixing-github-security-alerts -a claude-code -g -y

安装 repo 全部 skill

npx skills add Tracer-Cloud/opensre --all -g -y

预览 repo 内 skill

npx skills add Tracer-Cloud/opensre --list

SKILL.md

Frontmatter
{
    "name": "fixing-github-security-alerts",
    "metadata": {
        "owner": "Vaibhav",
        "version": "1.0",
        "requires": [
            "GitHub authentication with repository write access and security-events read access.",
            "An installed and authenticated coding agent.",
            "The fix_github_security_alert tool and its supported local execution environment."
        ],
        "usecases": [
            "For repository maintainers remediating Dependabot, CodeQL, or code-quality alerts.",
            "For users requesting a fix from an exact security alert or repository security page."
        ],
        "last_changed_at": 1789171200,
        "last_changed_by": "Jan"
    },
    "description": "Remediate GitHub security \/ Dependabot \/ CodeQL \/ code-quality alerts via fix_github_security_alert"
}

GitHub security and quality fix

Use fix_github_security_alert to remediate a supported security or quality finding, producing a local diff or a pull request as requested.

When to use

  • The user asks to fix/remediate GitHub security and quality issues, security alerts, Security and quality findings, Code Quality findings, Dependabot alerts, CodeQL/code-scanning alerts, vulnerable dependencies, or repo security issues.
  • The user says "hey fix the security issues", "fix the security issues in owner/repo", "fix the security and quality issues", or "fix the opensre repo security issues and raise a PR".
  • A GitHub security alert URL, /security/code-scanning page URL, or /security/quality URL is provided.

Scope

Use other workflows for these requests:

  • Ordinary GitHub issue/PR create, close, comment, assign, label, merge, or repo reads. Use github_cli.
  • Secret-scanning remediation. The tool will refuse it because the secret must be revoked/rotated outside the repo before code cleanup.

Workflow rules

  • For broad repo requests, call: fix_github_security_alert(owner?, repo?, alert_type="auto", open_pr=<user asked PR>) and let the tool select one open supported security or quality finding.
  • If no owner/repo is named, omit both and let the tool use the current checkout's GitHub origin.
  • If the user supplies an alert URL, /security/code-scanning page URL, or /security/quality URL, pass it as alert_url.
  • If they name a Dependabot alert, code-scanning alert, CodeQL alert, or Code Quality finding number, pass alert_type and alert_number.
  • Use alert_type="code_quality" for GitHub /security/quality standard findings such as unused import, empty except, unreachable code, or mixed returns.
  • Use alert_type="code_scanning" for GitHub /security/code-scanning pages or broad CodeQL/code-scanning requests.
  • Set open_pr=true only when they ask to open/raise/create a PR or "ship" the fix; otherwise leave it false for a local diff.
  • Never use github_cli to run a raw gh workflow around this. The fixer owns alert context, fix execution, branch safety, and PR creation.
  • The tool runs one alert per call. Do not loop over multiple alerts unless the user explicitly asks to continue after the first result.
  • The tool fixes findings itself: built-in fixers first, then an auto-detected coding agent CLI (no configuration needed). Never add coding-agent advice, CLI names, or install commands beyond what the tool's error text already says, and never make an external agent the user's next step.
  • If the tool returns response_text, output exactly that text and stop.
  • If the tool reports no automatic patch, reply in one short line from error. Do not say "next steps", do not add numbered options, do not list example commands, and do not ask a broad follow-up question.
  • After the tool returns, reply briefly from the result: finding type/number, changed files, and PR URL if present. If error_kind is set, explain the required next step from error.

Examples

  • "fix the security issues in Tracer-Cloud/opensre and raise a PR"

    fix_github_security_alert(owner="Tracer-Cloud", repo="opensre", alert_type="auto", open_pr=true)
    
  • "hey fix the security issues"

    fix_github_security_alert(alert_type="auto")
    
  • "fix the code quality findings on https://github.com/Tracer-Cloud/opensre/security/quality"

    fix_github_security_alert(alert_url="https://github.com/Tracer-Cloud/opensre/security/quality", alert_type="code_quality")
    
  • "fix Dependabot alert 12 in this repo"

    fix_github_security_alert(alert_type="dependabot", alert_number=12)
    
  • "fix https://github.com/acme/app/security/code-scanning/7 and open a PR"

    fix_github_security_alert(alert_url="https://github.com/acme/app/security/code-scanning/7", open_pr=true)
    
  • "fix the code scanning errors on https://github.com/Tracer-Cloud/opensre/security/code-scanning and raise a PR"

    fix_github_security_alert(alert_url="https://github.com/Tracer-Cloud/opensre/security/code-scanning", alert_type="code_scanning", open_pr=true)
    

Version History

  • 4303874 Current 2026-09-22 10:48

Same Skill Collection

core/agent_harness/prompts/skills/architecture_audit/SKILL.md
core/agent_harness/prompts/skills/delivering-morning-briefings/SKILL.md
core/agent_harness/prompts/skills/github_ci_fix_onboarding/SKILL.md
core/agent_harness/prompts/skills/github_ci_fix/SKILL.md
core/agent_harness/prompts/skills/github_ci_health/SKILL.md
core/agent_harness/prompts/skills/github_cli/SKILL.md
core/agent_harness/prompts/skills/github_security_fix/SKILL.md
core/agent_harness/prompts/skills/investigating-incidents-with-runbooks/SKILL.md
core/agent_harness/prompts/skills/morning_report/SKILL.md
core/agent_harness/prompts/skills/onboarding-github-ci/SKILL.md
core/agent_harness/prompts/skills/repair-github-ci/SKILL.md
core/agent_harness/prompts/skills/reporting-github-ci-failures/SKILL.md
integrations/github/tools/ci_fix/SKILL.md
integrations/github/tools/github_cli/SKILL.md
integrations/github/tools/security_fix/SKILL.md
integrations/github/tools/workflow/SKILL.md
integrations/posthog/tools/skills/posthog-summary/SKILL.md
integrations/posthog/tools/skills/summarizing-posthog-analytics/SKILL.md
integrations/sentry/tools/skills/sentry-summary/SKILL.md
integrations/sentry/tools/skills/summarizing-sentry-issues/SKILL.md
integrations/yandex_cloud/tools/SKILL.md
tools/github_cli/SKILL.md
tools/system/python_execution_tool/skills/github-star-velocity/SKILL.md
tools/system/python_execution_tool/skills/measuring-github-star-velocity/SKILL.md
core/agent_harness/prompts/skills/cicd_analytics_demo/SKILL.md

Metadata

Files
0
Version
4303874
Hash
db3af37d
Indexed
2026-09-22 10:48

Home - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-22 13:44
浙ICP备14020137号-1