refactoring-10-security-privacy
Checks for security and compliance issues in research Python codebases.
Install
mkdir -p .claude/skills/refactoring-10-security-privacy && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14767" && unzip -o skill.zip -d .claude/skills/refactoring-10-security-privacy && rm skill.zipInstalls to .claude/skills/refactoring-10-security-privacy
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when checking for data leaks, PII handling, and license risks in Python research code.Key capabilities
- →Scan for hardcoded secrets, tokens, or private endpoints
- →Identify PII fields and confirm storage and logging
- →Check dataset and library licenses for compatibility
- →Ensure .gitignore excludes sensitive outputs
- →Document security and privacy constraints in README.md
How it works
This skill systematically scans Python research code to identify and address potential data leaks, PII exposure, and license violations by checking for secrets, PII fields, and license compatibility.
Inputs & outputs
When to use refactoring-10-security-privacy
- →Scan for hardcoded API secrets
- →Identify PII in data processing flows
- →Check dataset license compliance
- →Sanitize git-tracked repositories
About this skill
Refactoring 10: Security and Privacy
Goal
Reduce risk of data leakage, PII exposure, or license violations.
Sequence
- Order: 10
- Previous: refactoring-09-performance-profiling
- Next: refactoring-11-ci-automation
Workflow
- Scan for hardcoded secrets, tokens, or private endpoints.
- Success: Secrets and risky endpoints are identified.
- Identify PII fields and confirm how they are stored and logged.
- Success: PII fields and handling are documented.
- Check dataset and library licenses for compatibility.
- Success: License constraints are verified and noted.
- Ensure
.gitignoreexcludes sensitive outputs and large artifacts.- Success: Sensitive outputs are not tracked by git.
- Document required security or privacy constraints in
README.md.- Success: README describes required constraints and handling rules.
Guardrails
- Do not delete or redact data without approval.
- Escalate if sensitive data is discovered.
- Keep changes minimal and focused on safety.
Limitations
- →The skill does not delete or redact data without approval
- →The skill requires escalation if sensitive data is discovered
How it compares
This skill provides a structured workflow for security and privacy auditing in Python research code, ensuring specific checks for secrets, PII, and licenses, unlike a general code review.
Compared to similar skills
refactoring-10-security-privacy side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| refactoring-10-security-privacy (this skill) | 0 | 7mo | No flags | Intermediate |
| backend-security-coder | 24 | 4mo | No flags | Intermediate |
| security-audit | 3 | 6mo | Review | Intermediate |
| codeql | 1 | 2mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by Silviase
View all by Silviase →You might also like
backend-security-coder
sickn33
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
security-audit
ruvnet
Comprehensive security scanning and vulnerability detection. Includes input validation, path traversal prevention, CVE detection, and secure coding pattern enforcement. Use when: authentication implementation, authorization logic, payment processing, user data handling, API endpoint creation, file upload handling, database queries, external API integration. Skip when: read-only operations on public data, internal development tooling, static documentation, styling changes.
codeql
trailofbits
Runs CodeQL static analysis for security vulnerability detection using interprocedural data flow and taint tracking. Applicable when finding vulnerabilities, running a security scan, performing a security audit, running CodeQL, building a CodeQL database, selecting query rulesets, creating data extension models, or processing CodeQL SARIF output. NOT for writing custom QL queries or CI/CD pipeline setup.
cookbook-audit
anthropics
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.