krone9/pi-superpowers/security
- community
Checking that the SKILL.md file is still in the repository.
Scan the codebase for security vulnerabilities — hardcoded secrets, injection risks, exposed credentials, insecure patterns. Use when the user types /security or asks for a security audit.
Install
npx vskill@latest install krone9/pi-superpowers/securitySKILL.md
Task: Security scan
Scan the codebase for security issues. This is a structured audit across 4 categories. Report findings before asking to fix anything.
Step 1: Secrets and credentials scan
Search for hardcoded secrets, API keys, tokens, passwords:
Also check for common patterns:
sk-,ghp_,glpat-,xox(Slack),AKIA(AWS) prefixes- Anything that looks like a JWT (
eyJ...) - Base64 strings in non-test code that are unusually long
Step 2: Injection vulnerabilities
Look for:
- SQL strings built with string concatenation or template literals instead of parameterised queries
eval(),exec(),subprocess.shell=True, or similar dynamic code execution- Unvalidated user input passed directly to file paths, shell commands, or database queries
- XSS vectors: unsanitised user content rendered as HTML (
innerHTML,dangerouslySetInnerHTML)
Step 3: Authentication and authorisation
Check for:
- Routes or endpoints with no auth middleware
- JWT tokens without expiry
- Passwords stored as plaintext or weak hashes (MD5, SHA1)
- Missing rate limiting on login or sensitive endpoints
- CORS configured as
*in production code
Step 4: Data exposure
Look for:
- Sensitive fields returned in API responses that shouldn't be (passwords, internal IDs, tokens)
- Error messages that expose stack traces, file paths, or internal details
- Logging of sensitive user data
- Files or directories exposed that shouldn't be (e.g.
.envin a public folder)
Step 5: Output the security report
Step 6: Save the report
Write the report to docs/security-audit.md with today's date. Append if file exists, don't overwrite history.
Do not fix anything until the user reviews the report and confirms.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/security/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/krone9/pi-superpowers/security)