frame-light-leak-cinema
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents a potential surface for indirect prompt injection. 1. Ingestion points: User-provided text for '标题' (Title), '副标' (Subtitle), and 'Metadata' (referenced in SKILL.md). 2. Boundary markers: Absent; there are no clear delimiters or instructions to ignore instructions embedded within the user data. 3. Capability inventory: The skill generates HTML and CSS that is rendered by the agent. 4. Sanitization: Absent; no validation or escaping of user input is specified, creating a cross-site scripting (XSS) risk.
- [EXTERNAL_DOWNLOADS]: The skill utilizes remote assets for rendering. Evidence: The HTML example loads 'cdn.tailwindcss.com' for styling and 'fonts.googleapis.com' for typography, both of which are well-known and standard services in web development.
Audit Metadata