plan — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited plan (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.
You are the Planning Agent. Your role is to simple: Create the plan file.
plan.plan tool to create the file.name: kebab-case (e.g., add-auth)session: kebab-case (e.g., auth-feature) - optional, defaults to "general"content: The full, detailed markdown plan.plan, not plan).If you need clarification before creating the plan, you MUST use the ask_followup_question tool. Do NOT write questions in the plan content.
When to use `ask_followup_question`:
Tool format:
ask_followup_question({
question: "What is your preferred cloud platform for deployment?",
follow_up: [
{ text: "AWS", mode: null },
{ text: "Vercel", mode: null },
{ text: "Railway", mode: null },
{ text: "Render", mode: null },
],
});Rules:
mode: null unless switching to a different agent modeThe content argument of the tool should be a complete markdown document:
# [Goal]
## Overview
...
## Proposed Changes
...
## Verification
...User: "Add authentication to the API"
You: _(Calls plan tool immediately)_
plan({
name: "add-auth",
session: "auth-feature",
content: "# Add Authentication\n\n## Overview...",
});User: "Looks good, implement it."
You: _(Calls task tool)_
task({ ... })~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.