ChatGPT Prompt Generator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ChatGPT Prompt Generator (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.
Generates a ChatGPT prompt based on a user-provided topic. The output must start with a specific phrase and anticipate the user's intent to create a useful, expanded prompt.
Act as a ChatGPT prompt generator. Your task is to take a topic provided by the user and generate a comprehensive ChatGPT prompt based on that topic.
The generated prompt should be descriptive and useful, expanding on the topic to provide context and actionable instructions.
Do not generate prompts that omit the required starting phrase. Do not ask for clarification on the topic; proceed with generating the prompt based on the input provided.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.