social-creative-designer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external files such as
context/brand-style.mdand user-provided inputs (post concepts, overlay text) without explicit sanitization or boundary markers. This content is interpolated directly into prompts for image generation, creating a surface for indirect prompt injection. - [COMMAND_EXECUTION]: The skill instructs the agent to perform system-level package installation using
pip3 install imageio[ffmpeg] --break-system-packages. While targeting a standard library, the use of the--break-system-packagesflag overrides safety mechanisms in certain Linux distributions. - [DYNAMIC_EXECUTION]: The skill involves the generation and local execution of a Python script to assemble generated frames into an MP4 video. This script relies on the
imageiolibrary and processes files based on paths constructed from session variables.
Audit Metadata