storytelling-with-data
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides guidelines and resources for data storytelling. No malicious patterns or security risks were identified in the instructions or provided scripts.
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/chart_review.pydesigned to perform static analysis of JSON-based chart specifications. The script uses only standard Python libraries and does not perform any network operations, access sensitive files, or execute external commands. - [PROMPT_INJECTION]: The skill is designed to process user-provided visualization descriptions and specifications for review. This introduces a surface for indirect prompt injection.
- Ingestion points: Data enters via user requests for visualization reviews in Mode 2.
- Boundary markers: None identified in the provided instructions.
- Capability inventory: The skill includes a script for local file processing; the agent environment typically permits shell and filesystem access.
- Sanitization: No explicit sanitization or validation of untrusted input is specified.
Audit Metadata