Babysitter security-review
Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.
install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/rpikit/skills/security-review" ~/.claude/skills/a5c-ai-babysitter-security-review && rm -rf "$T"
manifest:
library/methodologies/rpikit/skills/security-review/SKILL.mdsource content
Security Review
Overview
Identify security vulnerabilities in code changes. Covers OWASP categories, injection vectors, authentication/authorization issues, data exposure, and dependency risks.
When to Use
- After code review passes (or in parallel)
- Before any code merge involving user-facing changes
- As part of the /review-security command
- Mandatory for high-stakes implementations
Process
- Identify modified files with security relevance
- Scan for common vulnerability patterns
- Assess authentication and authorization changes
- Check for data exposure risks
- Evaluate dependency security
- Classify severity and provide recommendations
Severity Levels
- Critical: Immediate exploitation risk
- High: Significant vulnerability requiring fix before merge
- Medium: Vulnerability that should be addressed soon
- Low: Minor security improvement opportunity
Key Rules
- Security review failure halts implementation
- All findings must include file paths and line numbers
- Provide actionable remediation steps
- Reference OWASP categories where applicable
Tool Use
Invoke via babysitter process:
methodologies/rpikit/rpikit-review