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.py designed 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
Risk Level
SAFE
Analyzed
May 16, 2026, 01:22 PM
Security Audit — agent-trust-hub — storytelling-with-data