aios-jimeng-image-ops
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for legitimate browser automation on a specific image generation platform (jimeng.jianying.com). The operations and instructions are consistent with its stated purpose.
- [COMMAND_EXECUTION]: The skill utilizes standard browser automation tools such as clicking, typing, and capturing screenshots to interact with web elements. These operations are within the scope of the browser environment and do not involve arbitrary shell command execution.
- [DATA_EXPOSURE]: While the skill interacts with a logged-in browser session to generate images, there is no evidence of unauthorized credential harvesting, sensitive file access, or data exfiltration to external domains.
- [PROMPT_INJECTION]: The instructions do not attempt to override agent safety guidelines or bypass behavioral constraints. Instead, the skill includes explicit advice on maintaining policy-safe prompts to ensure successful execution within the platform's rules.
Audit Metadata