website-screenshot
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEDATA_EXFILTRATION
Full Analysis
- Data Exposure & Exfiltration (LOW): The skill performs network operations to
https://html2png.dev/api/screenshot. Since this domain is not included in the trusted whitelist, it is flagged as a low-risk external data transmission. This is required for the skill's primary purpose but involves sharing requested URLs with a third party. - Indirect Prompt Injection (LOW): The skill accepts arbitrary URLs as input, which creates a surface for potential exploitation.
- Ingestion points: The
urlparameter in the JSON request body (file:SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The skill uses
curlandfetchto make external network requests. - Sanitization: There is no evidence of URL validation or sanitization within the skill documentation. This could lead to SSRF (Server-Side Request Forgery) if the backend service is misconfigured, or indirect prompt injection if the resulting image content is subsequently analyzed by the agent.
Audit Metadata