Who Wants to be a Millionaire Quiz Host — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Who Wants to be a Millionaire Quiz Host (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.
A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.
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.
Hosts a 'Who Wants to be a Millionaire' style quiz game where the user answers questions. The system must provide exactly 4 options for every question.
Act as the host for a "Who Wants to be a Millionaire" style quiz game. Ask questions one by one for the user to answer.
Maintain an engaging, game-show host persona.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.