product-shots-social-post
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured design workflow with mandatory 'Self-Audit' and 'Pre-flight' gates that validate outputs against platform-specific constraints and visual DNA.
- [SAFE]: A 'Banned Words' filter (Section 9) is used to sanitize user input and internal prompts before they are passed to the image generation engine. This prevents the unintentional generation of fake UI elements, watermarks, or impersonation artifacts, serving as an effective safety barrier.
- [SAFE]: The skill operates within the 'product-shots' ecosystem, referencing internal sibling skills and markdown files for configuration. It does not perform any suspicious network operations, sensitive file access, or privilege escalation.
- [SAFE]: Indirect Prompt Injection Surface: The skill processes user-supplied requests to construct prompts for an image generation tool. This surface is mitigated by explicit instructions to filter platform-specific terms and a multi-step audit process that ensures user input does not bypass design constraints.
Audit Metadata