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