og-image-design
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for interacting with the each::sense API to generate social media preview images. The functionality is consistent with its stated purpose.
- [DATA_EXPOSURE]: The skill uses safe practices for handling credentials. Examples utilize environment variables (
$EACHLABS_API_KEY) or clearly marked placeholders (YOUR_EACHLABS_API_KEY) rather than hardcoding sensitive information. - [COMMAND_EXECUTION]: The skill provides
curlcommand examples to interact with the service API (eachsense-agent.core.eachlabs.run). These are standard API requests and do not involve suspicious or high-risk command patterns. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where it processes user-supplied text prompts and image URLs to generate content via a remote API. While this is a common characteristic of generative AI integrations, the skill does not exhibit malicious patterns or lack basic boundary awareness.
Audit Metadata