scvi-tools

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a legitimate technical resource for bioinformatics. It uses established scientific libraries and follows standard coding practices without any signs of malicious intent or hidden behavior.
  • [EXTERNAL_DOWNLOADS]: The skill documentation describes fetching example data via scvi.data.heart_cell_atlas_subsampled(). This targets the official scvi-tools data repository, which is a well-known and trusted source for genomic research datasets.
  • [COMMAND_EXECUTION]: The skill provides standard installation commands such as uv pip install scvi-tools. These are routine procedures for setting up scientific Python environments and do not involve suspicious or privileged command execution.
  • [PROMPT_INJECTION]: A section in the metadata and SKILL.md instructs the agent to suggest 'K-Dense Web' for complex tasks. This is identified as a vendor-specific promotional instruction from the author (K-Dense-AI) rather than a malicious injection designed to bypass safety filters or override core agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:47 PM