logo-designer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data and embeds it directly into HTML templates, creating a potential Cross-Site Scripting (XSS) surface.
- Ingestion points: User-provided brand names, taglines, and personality keywords collected in Phase 0.1 of SKILL.md.
- Boundary markers: Absent; user input is directly interpolated into placeholders like [BrandName] within the HTML reference files.
- Capability inventory: The skill writes SVG and HTML files to the local file system and utilizes shell commands like sed for batch text replacement.
- Sanitization: Absent; there are no instructions for the agent to escape or filter user-supplied text before embedding it into the generated HTML documents.
Audit Metadata