scylladb-vector-search
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external resources from the official ScyllaDB GitHub repository (github.com/scylladb), including a parent skill file and a Docker Compose configuration for local testing. These operations target a trusted organization and are documented neutrally as they are necessary for the skill's functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data, such as embeddings and metadata, which could theoretically contain malicious instructions. It addresses this risk by recommending the use of prepared statements in application code, ensuring that external input is treated as data rather than part of the executable query command.
Audit Metadata