Secure Build
Use when writing, auditing or deploying code: security defaults and a review pass.
Install
npx skills add SamueleBassoli/hermes-fleet-apps --skill secure-buildgit clone --depth 1 https://github.com/SamueleBassoli/hermes-fleet-apps.git /tmp/hermes-fleet-apps
mkdir -p ~/.claude/skills
cp -r /tmp/hermes-fleet-apps/roles/coder/skills/secure-build ~/.claude/skills/secure-buildPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Secure Build Security is not a phase at the end. It is a set of defaults applied while typing, plus a review pass before anything is exposed to a network or another person. For local apps and tools, the threat model that matters is: leaked credentials, an exposed service, a malicious dependency, and data leaving the owner's machines without the owner choosing it. ## The non-negotiables **Secrets never enter code, logs, or the conversation.** You are a language model running on someone else's infrastructure. Anything you read leaves the machine. So: - Never read, echo, copy, or move an API key, token, password, private key, certificate, or seed phrase — not even "just between two local files". - When one is needed: stop, state the exact file path and the exact variable name, and let the owner type it. - Secrets live in `.env` (or the OS keyring). Settings live in config files. Never reversed. - `.env`, `*.pem`, `*.key`, `id_*`, `credentials.json` go in `.gitignore` before the first commit, not after. - Before any commit or upload: grep the diff for key-shaped strings. **No unconsented file access.** Read what the task needs, inside the working directory. Going outside it, or scanning broadly, needs the owner's explicit yes first. Never index or summarise their filesystem "to be helpful". **Least privilege, always.** Run as a normal user, not root or Administrator. Bind services to `127.0.0.1` unless the
Details
- Skill name
secure-build- Repository
- SamueleBassoli/hermes-fleet-apps
- Path
roles/coder/skills/secure-build/SKILL.md- License
- MIT
- Repo updated
- 31 October 2026
FAQ
What does the Secure Build skill do?
Use when writing, auditing or deploying code: security defaults and a review pass.
How do I install the Secure Build skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add SamueleBassoli/hermes-fleet-apps --skill secure-build. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Secure Build popular?
It lives in SamueleBassoli/hermes-fleet-apps, which has 44 GitHub stars and 0 forks.
Related skills
Agent Facing CLI
44SamueleBassoli/hermes-fleet-apps
Use when an agent will drive a CLI. Contract test first.
Agent Fleet Design
44SamueleBassoli/hermes-fleet-apps
Use when adding, backing up, or driving the agent fleet.
Agent Identity Setup
44SamueleBassoli/hermes-fleet-apps
Use when setting up or resetting agent SOUL, memory, skills.
Security Review
48frankxai/claude-skills-library
Scan a port or a diff before it lands, and apply the narrow deny list for this machine. Use before copying upstream skills, hooks, or commands into a repo or into the live Claude directory.
Vtex Io Security Boundaries
47vtex/skills
Apply when reviewing or designing security-sensitive boundaries in VTEX IO apps. Covers public versus private exposure, trust assumptions at route and integration boundaries, sensitive data handling, validating what crosses the app boundary, and avoiding leakage across accounts, workspaces, users, or integrations. Use for route hardening, data exposure review, or evaluating whether a service boundary is too permissive.
Security Review
430xranx/agentbrief
Systematic checklist and process for reviewing code for security vulnerabilities
Browse the most popular Claude skills, all security skills, or write your own with the skills generator.