authoring-a-skill — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited authoring-a-skill (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A skill captures a durable, repeatable procedure so it doesn't have to be re-derived. Write one when you've solved something you'll plausibly hit again.
one-off answer or project-specific trivia (that belongs in memory/AGENTS.md).
./.korgex/skills/<kebab-name>/SKILL.md (project)or ~/.korgex/skills/<kebab-name>/SKILL.md (global). Frontmatter:
---
name: <kebab-name>
description: <one line — used to decide when to load it>
version: 1.0
trust: user
---order, and the checks. Keep it tight — it's injected by description and loaded on demand, so the body should be actionable, not an essay.
deciding to use it, so make it specific and trigger-able.
trust: user. korgex's own learned skills are trust: agent; neverhand-edit a built-in.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.