ads-photoshoot

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it interpolates user-supplied product descriptions directly into image generation prompt templates. While this is the core functionality, it lacks explicit sanitization or boundary markers to prevent the user input from overriding the intended photography style.
  • Ingestion points: User-provided product description text and local brand-profile.json configuration file.
  • Boundary markers: The skill uses template strings (e.g., "[product description], professional product photography...") but does not include explicit instructions to the generator to ignore embedded commands within the description.
  • Capability inventory: Uses the /banana generate tool to create images and performs file system write operations to the ./product-photos/ directory.
  • Sanitization: No input validation or escaping is performed on the product description before it is incorporated into the final prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 06:21 PM