sanitize

What problem does it solve?

Automatically detect and separate configuration values, credentials, and memory-like facts from arbitrary input to prevent accidental leaks, misconfigured manifests, and misplaced knowledge. The Skill helps ensure that secrets are routed to secure stores, base configuration stays overlay-friendly, and observations are recorded into shared memory rather than code.

Core Features & Use Cases

• Content Classification & Splitting: Identify config, credential, and memory fragments in mixed text and split them for separate handling.
• Secrets and Pattern Scanning: Use regex-driven patterns to flag private keys, API tokens, and inline credential assignments during diffs or pasted content.
• Manifest Validation: Apply base-manifest checks and allowlists to catch public domains, hardcoded IPs, and other environment-specific values and recommend overlayed config.
• Integrations & Outcomes: Route credentials to a password store, update Alfred-owned configs or overlays, and persist facts to shared agent memory; useful for pre-commit scans, code review automation, or CI validation.

Quick Start

Ask the skill to sanitize the provided content by passing the text as $ARGUMENTS so it classifies parts, validates manifests, routes credentials to the password store, and reports findings.