website-screenshot

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied URLs to generate website screenshots. This represents a potential indirect prompt injection surface where the content of a rendered page could be used to influence the agent's behavior via visual analysis.
  • Ingestion points: The url parameter provided by the user in the API request examples.
  • Boundary markers: None present in the provided instructions.
  • Capability inventory: Performs network POST requests to html2png.dev to submit screenshot tasks and receives a URL to the resulting image.
  • Sanitization: No explicit sanitization or validation of the target URL content is performed by the skill instructions.
  • [DATA_EXFILTRATION]: The skill transmits the target URL to the vendor-owned domain html2png.dev. This is the intended primary purpose of the skill and aligns with the vendor resource pattern for 'html2png'.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 11:23 AM