charting
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes industry-standard Python libraries for data visualization, including seaborn, matplotlib, and graphviz.
- [SAFE]: All file operations are directed to designated directories (/home/claude/ and /mnt/user-data/outputs/), adhering to expected environment constraints for an AI agent.
- [SAFE]: The skill contains no evidence of obfuscated code, unauthorized network requests, credential harvesting, or attempts to access sensitive system files.
- [PROMPT_INJECTION]: Indirect prompt injection surface analysis:
- Ingestion points: The skill is designed to process user-provided or agent-generated data to create visualizations.
- Boundary markers: None explicitly defined in the instructional text.
- Capability inventory: Writes image files to the filesystem using library-native functions (plt.savefig, g.render).
- Sanitization: Standard library usage for visualization typically handles data as content; the skill does not exhibit exploitable dynamic execution of the data itself.
- Risk assessment: This represents a standard functional surface for data visualization tasks and does not contain malicious instructions.
Audit Metadata