bio-data-visualization-interactive-visualization
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill utilizes well-established Python and R libraries (Plotly, Bokeh, Pandas) for data visualization. All code snippets align with the stated purpose of creating interactive plots for omics data analysis.
- DATA_EXPOSURE (SAFE): While the skill writes files to the local filesystem (e.g., .html, .json, .png), this is the primary function of the tool. No patterns of sensitive file access (e.g., SSH keys, credentials) or network-based exfiltration were found.
- INDIRECT_PROMPT_INJECTION (LOW): The skill possesses a surface for indirect injection as it processes external dataframes into HTML plots.
- Ingestion points: Dataframes such as
df,de, andde_resultsinSKILL.md. - Boundary markers: None present in the code snippets.
- Capability inventory: File writing via
fig.write_htmlandbokeh.io.save. - Sanitization: None explicitly implemented in the snippets, though underlying libraries (Plotly/Bokeh) provide default escaping for HTML attributes. The risk is minimal and restricted to the rendering of the generated HTML.
Audit Metadata