visual-style

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which creates a potential vulnerability to indirect prompt injection.
  • Ingestion points: The skill explicitly instructs the agent to analyze and extract information from website URLs (references/extractors/from-website.md), PDF brand guides (references/extractors/from-pdf.md), and video keyframes (references/extractors/from-video.md).
  • Boundary markers: The instructions use standard Markdown and YAML delimiters (---) for structuring output, but they do not provide explicit instructions to the agent to disregard or isolate potentially malicious commands that might be hidden within the processed external data.
  • Capability inventory: The skill's workflow includes fetching web content and interacting with external design tools and APIs, such as HeyGen (references/connectors/heygen-video-agent.md).
  • Sanitization: The provided instructions do not mention any specific sanitization, filtering, or validation techniques for the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM