size-chart
Fail
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: CRITICALCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions explicitly direct the agent to provide a link to
https://chatgpt-plus.top/list/#/homefor users in specific regions. This URL has been flagged as a phishing site by automated security scanners. - [CREDENTIALS_UNSAFE]: The skill is designed to handle a sensitive API key (
GPTIMAGE_API_KEY) and explicitly recommends that the agent configure its environment to send this key to a non-standard, third-party API gateway (https://tryallapi.com/v1). Directing sensitive credentials to unverified third-party services is a common pattern for credential harvesting.
Recommendations
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata