brand-context — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited brand-context (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
You are establishing the brand context foundation. This file is read by every other brand skill before doing any work. Your job is to capture all core brand information in a structured, reusable format.
Find or create the brand package. Look for brand.yaml (in ./, ./brand/, or brands/<slug>/).
brand.yaml + context.md; ask the user what to update.brand-init first to scaffold it (see that skill / references/brand-package-spec.md), then collect the information below..agents/brand-context.md from an older run → read it and migrate its content into <package>/context.md.Ask for the following. If the user has already provided it in conversation, don't ask again.
Write the brand DNA to `<package>/context.md` (inside the brand package — NOT .agents/), with this structure:
# Brand Context
## Brand
- **Name**: [name]
- **Category**: [category]
- **Description**: [one-liner]
- **Stage**: [stage]
- **Website**: [url or N/A]
## Audience
- **Primary Audience**: [description]
- **Key Problem**: [problem they face]
- **Their Language**: [phrases, words they use]
## Positioning
- **Differentiation**: [what makes this brand different]
- **Competitors**: [list]
- **Market Position**: [premium / value / niche / mass]
## Brand Personality
- **Personality Words**: [word, word, word]
- **Tone**: [formal/casual, serious/playful]
- **Voice Admires**: [brand names or "none"]
## Values & Mission
- **Core Values**: [value, value, value]
- **Mission**: [mission statement]
## Goals
- **Primary Goal**: [goal]
- **Key Metrics**: [metrics]Then update the manifest so the package stays queryable:
artifacts.context: true in brand.yaml, and refresh updated.brand.yaml's one_liner, name, industry, or archetype are still blank and you now know them, fill them in by editing brand.yaml directly. (If the brand-init skill is installed alongside this one, you may instead run its scripts/brand.sh set --package <package> --key one_liner --value "…" — but a direct edit always works and needs no sibling skill.)Tell the user the context is saved in the package and every other brand skill will read it automatically. They can update it anytime by running this skill again.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.