children-story-creator
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
helpers/python/format_children_storybook.py. This script is used to compile story text into a formatted.docxdocument. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided creative content and processes it through a formatting script, representing a potential injection surface.
- Ingestion points: User-supplied themes, characters, and story plot points are ingested via the agent prompt.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill definitions.
- Capability inventory: The agent has the capability to execute a local Python formatting script (
format_children_storybook.py) and write to the file system to create the output artifact. - Sanitization: The skill instructions do not specify any validation or sanitization routines for the story content before it is processed by the helper script.
Audit Metadata