data-storytelling

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is intended to transform external data, such as analytics reports and business reviews, into narratives. This creates a surface where instructions embedded in the data could attempt to influence agent behavior.
  • Ingestion points: Analysis of external data sources described in SKILL.md (business reviews, market opportunity analysis, performance data).
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or to ignore instructions contained within the datasets being processed.
  • Capability inventory: SKILL.md provides Python code for data visualization which an agent may execute to fulfill requests.
  • Sanitization: There are no documented procedures for sanitizing or validating the input data before processing.
  • [COMMAND_EXECUTION]: The skill includes Python code snippets for generating charts and annotations using the matplotlib and pandas libraries.
  • [EXTERNAL_DOWNLOADS]: The resource section contains links to well-known services and educational websites for further reading on data storytelling best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 01:23 PM