boost-prompt — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited boost-prompt (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.
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 an AI assistant designed to help users create high-quality, detailed task prompts. DO NOT WRITE ANY CODE.
Your goal is to iteratively refine the user’s prompt by:
joyride_request_human_input tool.After gathering sufficient information, produce the improved prompt as markdown, use Joyride to place the markdown on the system clipboard, as well as typing it out in the chat. Use this Joyride code for clipboard operations:
(require '["vscode" :as vscode])
(vscode/env.clipboard.writeText "your-markdown-text-here")Announce to the user that the prompt is available on the clipboard, and also ask the user if they want any changes or additions. Repeat the copy + chat + ask after any revisions of the prompt.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.