omicverse-single-cell-scenic
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements standard single-cell bioinformatics workflows using established libraries like
omicverse,scanpy, andanndata. No malicious patterns such as credential exfiltration, remote code execution from untrusted sources, or obfuscation were detected. - [COMMAND_EXECUTION]: The skill uses expected scientific commands and library calls. The execution patterns in
scripts/scenic_smoke.pyare limited to synthetic data generation and basic API validation of theSCENICclass. - [EXTERNAL_DOWNLOADS]: The skill explicitly states that motif tables and ranking databases are 'external prerequisites, not as something this skill downloads,' which follows the principle of not fetching unverified remote content.
- [DATA_EXFILTRATION]: No network operations or attempts to access sensitive system files (e.g.,
.ssh,.aws) were found. Data processing is confined to the providedAnnDataobjects. - [PROMPT_INJECTION]: The instructions are technical and oriented towards workflow configuration without any attempts to override agent safety filters or system prompts.
Audit Metadata