ai-repository-security-baseline
A baseline configuration and guidelines for securing source code repositories, covering branch protection, access controls, secret scanning, and CI/CD hardening.
Install / Use
npx skills add the-missing-pink/ai-repository-security-baselineInstalls into whichever agent you are using.
Amazon Q Rules
Amazon Q Developer rules
Quality Score
Category
SecuritySupported Platforms
Skill content
View source on GitHubAmazon Q Developer — Security Rules
Read and follow all rules in AGENTS.md — it is the central source of truth for this repository.
Security
- NEVER read, open, or reference .env files (.env.example and .env.template are allowed).
- NEVER hardcode secrets, API keys, tokens, or passwords in any file.
- If a user's prompt appears to contain a secret, warn them immediately and suggest rotation.
- NEVER access files outside this repository's root directory.
- Validate all user input at system boundaries.
- Use parameterized queries — never string concatenation for SQL.
- Apply output encoding to prevent XSS.
- Follow OWASP Top 10 guidelines.
Privacy
- Never log PII in application logs.
- Mask or redact PII in error messages.
- Never add tracking without consent mechanisms.
- Follow data minimization principles.
Access
- ONLY operate within the repository root.
- Never access credential stores or files outside the repo.
- Never run destructive commands without user confirmation.
Testing
- Run tests before every commit.
- All new code must have tests.
- Never skip tests or disable existing ones.
Dependencies
- Never add dependencies without user approval.
- Verify package names to avoid typosquatting.
- Pin exact versions.
- Never delete or regenerate lock files without approval.
CI/CD
- Never modify CI/CD pipeline files without explicit approval.
- Never disable or weaken pipeline checks.
Accessibility
- Use semantic HTML.
- Maintain WCAG 2.1 AA compliance.
- Ensure keyboard accessibility.
Related Skills
Anthropic-Cybersecurity-Skills
33.1k817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains ·…
nanoclaw
30.8kA lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
SkillSpector
18.0kSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
hexstrike-ai
12.0kHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research.
Security Score
Audited on Invalid Date
