seedance-2-prompts
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the vendor's API at
https://youmind.com/youhome-api/video-promptsto fetch prompt data. This is the primary function of the tool and uses the author's official infrastructure. - [COMMAND_EXECUTION]: The agent uses a local Node.js script (
scripts/search.mjs) to facilitate searches. The script is a simple wrapper for API requests and does not perform any sensitive system operations. - [PROMPT_INJECTION]: The skill processes and displays external content from community creators. While this constitutes an indirect prompt injection surface, the risk is typical for search-based skills and the content is curated by the vendor. No malicious instructions were detected in the skill's logic.
- [DATA_EXFILTRATION]: User search terms are transmitted to the vendor's domain (
youmind.com) to retrieve results. This is expected behavior for the skill's purpose and does not involve the transmission of sensitive local files or credentials.
Audit Metadata