Stats
Actions
Tags
Enforce confidentiality across Oracle deliverables: pre-delivery content scans, codename protocol enforcement, and git safety checks. Use before client handoffs, document sanitization, or committing deliverable content.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-skills-library:oracle-confidentialityThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Purpose:** Enforce confidentiality protocol across all Oracle AI Architect deliverables.
Purpose: Enforce confidentiality protocol across all Oracle AI Architect deliverables. Scope: Pre-delivery audit, codename enforcement, content sanitization. Authority: This skill has VETO power. If it fails, delivery is blocked.
Invoke:
Trigger: /oracle-confidentiality or automatically at end of solution design workflow
Run this checklist before any deliverable leaves the workspace:
Search all output files for:
- Real customer names (from conversation context)
- Industry-specific terms that could identify the client
- Geographic identifiers tied to the client
- Internal Oracle pricing not on public price list
- Competitor names used in attack mode (not just comparison)
Verify:
- Deliverables are in clients/[CODE]/deliverables/ (gitignored)
- SOLUTION-DESIGN.md is in clients/[CODE]/ (gitignored)
- No deliverables leaked to research/ or projects/ folders
- No codename appears in research/topics/ filenames
Before any commit:
- Run: git diff --cached -- check no client content staged
- Run: git status -- verify clients/ content is untracked
- Verify clients/.gitignore is intact and blocking deliverables
For every generated image:
- No Oracle logos (text labels only)
- No customer logos
- No identifiable customer branding or colors
- Service names match official Oracle branding
In every document:
- Customer referred to as "the organization" or "the customer"
- Solution name is generic or codename-based
- All data examples use synthetic/mock data
- No internal meeting notes or email quotes
When invoked, the agent should execute these checks:
Grep for known risks:
Verify .gitignore integrity:
Check git status:
Report:
If confidential data is accidentally committed:
This skill is called by:
Version: 1.0 | Created: 2026-02-09
npx claudepluginhub frankxai/claude-skills-library --plugin claude-skills-libraryBlocks unsafe code before commit with secret scanning, OWASP Top 10 detection, dependency audits (npm/pip/cargo), and permission checks. Hard security gate on critical findings.
Redacts reverse-engineering findings for public disclosure while preserving methodology and patterns. Covers private/public repo split, deny-list maintenance, orphan-commit publish pattern, and CI redaction gates.
Detects leaked secrets, API keys, passwords, and tokens in git repositories using gitleaks. Automatically sets up pre-commit hooks to scan staged files and block commits containing secrets.