lovart
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands including
curl,openssl,date, andawkto manage API requests and compute HMAC-SHA256 signatures for authentication. - [EXTERNAL_DOWNLOADS]: The skill references documentation and developer guides hosted on
lovart.info. The API communication targetslovart.ai, which is consistent with the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided natural language prompts for image and video generation.
- Ingestion points: User-provided design descriptions (e.g.,
<your-design-description>) are processed by the agent. - Boundary markers: None identified.
- Capability inventory: The skill uses
curlto transmit data to an external API endpoint. - Sanitization: No explicit sanitization or filtering of user input is specified in the skill instructions.
Audit Metadata