studio-design-onboarding-flow

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local project files to generate HTML and Markdown artifacts, creating a potential surface for indirect injection.\n
  • Ingestion points: The agent reads user-controlled files including docs/PRODUCT.md, productos/design/1-Product-Identity.md, and productos/design/2-Magic-Moment.md to extract product details, identity attributes, and magic moments.\n
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded in the ingested content.\n
  • Capability inventory: The agent writes the processed data into productos/design/3-Onboarding-Flow.md and productos/design/onboarding-wireframe.html. The generated HTML uses innerHTML to render text extracted from inputs, creating a cross-site scripting (XSS) surface within the generated local wireframe.\n
  • Sanitization: The instructions do not specify any validation or sanitization of the content before it is interpolated into the generated HTML and Markdown documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:33 PM
Security Audit — agent-trust-hub — studio-design-onboarding-flow