jimeng-opencli-image2image
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands using the
opencliutility to perform image-to-image tasks, including uploading reference images and processing text prompts. - [PROMPT_INJECTION]: The skill's workflow ingests untrusted user data which is interpolated into shell command templates, presenting a risk of indirect prompt injection or command injection if inputs are malicious.
- Ingestion points: User-provided text prompts and local file paths specified in the core flow and examples of
SKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined to isolate user-supplied strings from the command structure.
- Capability inventory: The skill possesses the capability to execute shell commands (
opencli jimeng generate-image2image). - Sanitization: There are no instructions for sanitizing, escaping, or validating the user-provided prompts or file paths before they are executed in the shell.
Audit Metadata