product-photography
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script
docs/creative_cli.pywith arguments like--product-nameand--promptwhich are derived from user input. This pattern creates a command injection surface if special characters in the user input are not properly handled by the agent during command construction. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product descriptions which are used to build prompts and CLI parameters.
- Ingestion points: User-provided product details collected during the intake workflow in
SKILL.md. - Boundary markers: The instructions lack specific delimiters or warnings to the agent to disregard malicious instructions embedded within the product descriptions.
- Capability inventory: The skill possesses the ability to execute shell commands (
python docs/creative_cli.py) and write files to theassets/directory. - Sanitization: There are no instructions for sanitizing or escaping the external content before it is interpolated into the shell command or the image generation prompt.
Audit Metadata