etsy-tony-full-from-reference

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided reference images, product photos, and a locally stored product-identity.json file. This data is used to drive the generation of new images and marketing copy. The instructions lack boundary markers or sanitization requirements to prevent malicious content in the inputs from influencing the agent's behavior. * Ingestion points: User-provided reference images, product photos, and the product-identity.json file. * Boundary markers: Absent. * Capability inventory: Local file writing, image generation via sub-skills, and programmatic image modification. * Sanitization: Absent.
  • [DYNAMIC_EXECUTION]: The skill requires the agent to use deterministic tools like Pillow, SVG, or HTML-CSS to overlay text and dimensions onto generated images. This involves generating and executing small code snippets at runtime based on product facts to perform image manipulations.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 02:56 PM