beautiful-data-viz
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The skill instructions in
SKILL.mdare focused on visualization tasks and do not contain any patterns attempting to override agent safety or system prompts. - Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file path access, or network operations to non-whitelisted domains were detected. The scripts focus entirely on local data processing and rendering.
- Unverifiable Dependencies (SAFE): The skill references well-known and trusted Python packages:
matplotlib,seaborn,pandas, andIPython. No remote scripts are downloaded or executed. - Indirect Prompt Injection (LOW): While the skill processes user-provided tabular data (DataFrames), it lacks dangerous capabilities like network exfiltration or file-writing. The risk of an attacker influencing agent behavior through data content is negligible in this context.
- Dynamic Execution (SAFE):
assets/beautiful_style.pyusesIPython'srun_line_magicto set a static configuration for retina display rendering. This is a standard and safe operation within a notebook environment and does not involve executing untrusted strings.
Audit Metadata