# Wrap

> Sanitize and delimit an operator directive (or other external input) into a closed-enum WrapKind envelope before it is injected into a planning/coding prompt — the data-not-instructions boundary. Use when external/operator free-text must be safely embedded in a prompt, when the user says "wrap this directive", or as the pre-injection step inside /code, /qna, /research, and /plan. Enforces an 8KB cap and refuses unknown kinds.

## Facts
- Page: https://tashan.sh/capability/skill-splockorg-wrap
- tashan id: skill:splockorg/wrap
- Source: https://github.com/splockorg/splock
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 100.0
- Freshness: 100.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: NOASSERTION
- Official: no

## Install

```sh
cp -r wrap ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-20 by tashan (https://tashan.sh) from public evidence. Scorer s5.