selling-point-infographic
Fail
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: CRITICALDATA_EXFILTRATIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill provides a link to
https://chatgpt-plus.top/list/#/home, which has been identified as a phishing site by automated security scanners. Additionally, thescripts/generate.pyutility is designed to transmit the user'sGPTIMAGE_API_KEYto external endpoints, including the default suggested domaintryallapi.com. - [EXTERNAL_DOWNLOADS]: The
scripts/generate.pyscript fetches image data from URLs returned by API responses and writes them to the local file system. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted user-supplied product descriptions and images and interpolates them into prompt templates for AI models. Evidence includes:
- Ingestion points: Product identity lock facts, user-approved marketing copy, and reference photos (SKILL.md).
- Boundary markers: The prompt templates lack clear delimiters or specific instructions to ignore embedded commands within the user-provided data.
- Capability inventory: The
scripts/generate.pyscript possesses capabilities for both network requests (via urllib) and local file writing. - Sanitization: There is no evidence of input validation, escaping, or filtering of user-provided strings before they are inserted into the model prompts.
Recommendations
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata