vector-search-recall-tests

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and code snippets follow established engineering practices for vector database evaluation. All external references and downloads target well-known, reputable technology documentation sites and benchmarking repositories.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to clone and install the 'ann-benchmarks' tool from its official GitHub repository. This is a well-known industry-standard tool for evaluating approximate nearest neighbor algorithms and is appropriate for the skill's primary purpose.
  • [COMMAND_EXECUTION]: Code examples demonstrate usage of standard database clients (Qdrant, Weaviate) to interact with local services (e.g., localhost:6333). These operations are restricted to the local environment and are intended for legitimate benchmarking tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 08:27 AM