scvelo
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: A thorough analysis of the skill's instructions, scripts, and references reveals no malicious patterns or security risks. The skill is designed for standard bioinformatics research workflows.
- [PROMPT_INJECTION]: The instructions contain no patterns designed to override agent behavior, bypass safety filters, or extract system prompts.
- [EXTERNAL_DOWNLOADS]: All external references point to reputable sources, including the official scVelo documentation on ReadTheDocs and its source code on GitHub. The recommended installation uses the standard Python package registry (PyPI).
- [COMMAND_EXECUTION]: The provided Python script executes standard data analysis routines. No instances of arbitrary shell command execution, privilege escalation (e.g., sudo), or persistence mechanisms were found.
- [DATA_EXFILTRATION]: File access is limited to reading genomic count matrices and writing analysis outputs to a local directory. There are no unauthorized network operations or patterns associated with credential harvesting.
Audit Metadata