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 opencli utility 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
Risk Level
SAFE
Analyzed
Jul 28, 2026, 03:33 AM
Security Audit — agent-trust-hub — jimeng-opencli-image2image