ig-carousel
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for using shell commands, such as
curlfor uploading media to pre-signed URLs and headless browsers for rendering HTML designs into images. These operations are necessary for the skill's primary function of media preparation and publishing. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied ideas and external voice profile files to generate content. It implements security best practices by requiring explicit human approval of all generated slide copy and captions before the final files are rendered or published.
- [SAFE]: The skill accesses vendor-specific configuration data stored in
~/.uplika/and interacts with the official vendor dashboard. These actions are transparent and consistent with the intended integration between the agent and the Uplika service.
Audit Metadata