jmstar85/oh-my-githubcopilot/security-scan
Claude Code and agent skill by jmstar85/oh-my-githubcopilot
- community
Checking that the SKILL.md file is still in the repository.
Rapid security scanning workflow for code changes. Activates a focused security sweep. Activate when: security scan, scan for vulnerabilities, check for secrets, security check, run security audit, check deps.
Install
npx vskill@latest install jmstar85/oh-my-githubcopilot/security-scanSKILL.md
The same SKILL.md was published earlier as zereight/gitlab-mcp/security-scan.
Security Scan
Rapid security sweep for code changes. Faster than a full /review — focused on security only.
When to Use
- Before committing code that touches auth, user input, data storage, or external APIs
- After adding new dependencies
- Quick pre-PR security gate
Scan Protocol
Step 1: Determine Scope
Step 2: Secrets Scan
CRITICAL: Any match in committed code = immediate blocker.
Step 3: Dependency Audit
Run language-appropriate audit:
Report: Count of critical/high severity CVEs and their package names.
Step 4: Input Validation Spot-Check
For changed files that handle user input (API endpoints, form handlers, CLI args):
- Is input validated/sanitized before use?
- Are SQL queries parameterized (no string concatenation)?
- Is HTML output escaped before rendering?
- Are file paths sanitized (no
../traversal)?
Step 5: Auth/Authz Quick Check
For changed files touching auth:
- Is authentication checked BEFORE authorization?
- Are authorization checks on EVERY relevant endpoint?
- Are JWT tokens validated (algorithm + signature + expiry)?
- Are session cookies
HttpOnly; Secure; SameSite=Strict?
Output Format
Severity Quick Reference
| Finding | Severity | Action | |
|---|---|---|---|
| Hardcoded secret in committed file | CRITICAL | Rotate key + remove from history | |
| Critical CVE in direct dependency | HIGH | Update package immediately | |
| SQL injection risk | CRITICAL | Parameterize query before PR | |
| Missing auth check on endpoint | HIGH | Add before PR | |
| High CVE in transitive dependency | MEDIUM | Track in backlog | |
| HTTP instead of HTTPS | MEDIUM | Enforce HTTPS redirect |
See Also
@security-reviewer— comprehensive OWASP Top 10 security review/review— full code review including security/coding-standards— baseline code quality rules
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingvscode-omg/resources/templates/skills/security-scan/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jmstar85/oh-my-githubcopilot/security-scan)