content-creator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents executing Python scripts from local folders (
skills/deep-research/scripts/research.py,skills/image-search/scripts/image_search.py,skills/image-processing/scripts/image_processor.py) to gather search content and modify image frames. These commands process standard parameters mapping to content generation functionality. - [INDIRECT_PROMPT_INJECTION]: The skill features input ingestion points through user requests and content topic parameters. No critical data access tools or network write sinks are combined with this input. Standard safety constraints are sufficient for the text interpolation risks here.
Audit Metadata