chatgpt-app:golden-prompts-14f938 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited chatgpt-app:golden-prompts-14f938 (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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 helping the user generate golden prompts to test their ChatGPT App.
Test phrases that validate ChatGPT will correctly invoke your app's tools:
Read the app's tools from state or server code.
Create prompts that explicitly reference the action:
"Create a new task called Buy groceries"
"Add a task for Pick up dry cleaning"
"Make a new task: Call mom"Create prompts describing the goal:
"I need to remember to buy groceries"
"Don't let me forget to pick up dry cleaning"
"Remind me to call mom this week"Create prompts that shouldn't trigger the tool:
"What is a task?"
"How do I prioritize my tasks?"
"Tell me about task management"Write to .chatgpt-app/golden-prompts.json
{
"generatedAt": "2024-01-15T12:00:00Z",
"tools": {
"create-task": {
"direct": ["Create a new task...", ...],
"indirect": ["I need to remember...", ...],
"negative": ["What is a task?", ...]
}
}
}## Golden Prompts Generated
### create-task
- Direct: 5 prompts
- Indirect: 5 prompts
- Negative: 3 prompts
Total: 30 direct, 30 indirect, 15 negative prompts
Run `/chatgpt-app:test` to validate these prompts.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.