ai-artist
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides Python scripts (
generate.py,search.py,extract_prompts.py) to manage prompt databases and execute image generation commands. These scripts are intended for local execution and handle file I/O for images and CSV data.\n- [EXTERNAL_DOWNLOADS]: Thegenerate.pyscript communicates with Google's GenAI API using the officialgoogle-genailibrary. This is a well-known service and the primary purpose of the skill.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it interpolates user-provided concepts into prompt templates without sanitization or boundary markers. \n - Ingestion points: The
conceptargument inscripts/generate.py.\n - Boundary markers: Absent; user input is directly substituted or replaces regex patterns in templates.\n
- Capability inventory: The final prompt is processed by the
generate_imagefunction which calls the Google GenAI API.\n - Sanitization: Absent. Since this is the primary functionality for an image generator, the risk is considered low and addressed by the model's own safety filters.
Audit Metadata