dreamina-opencli-text2image
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary function is to execute shell commands using the
opencliutility. These commands interact with the Jimeng (ByteDance) web service to generate images and manage user sessions. - [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it takes untrusted user input (the image generation prompt) and interpolates it into a shell command line.
- Ingestion points: The
<prompt>argument used inopencli jimeng generateandopencli jimeng generate-image2imagewithinSKILL.md. - Boundary markers: While documentation examples use double quotes around the prompt, there are no explicit instructions for the agent to escape shell metacharacters (e.g., semicolons, backticks, or pipe symbols).
- Capability inventory: The skill utilizes shell execution for subcommands including
generate,history,new,workspaces,user_credit,user_subscription, anduser_assets. - Sanitization: No sanitization or validation logic is defined to prevent command injection from malicious user input.
Audit Metadata