landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute an internal script (
marketing-skill/content-production/scripts/brand_voice_analyzer.py) to process user-provided content. This is a functional requirement for brand alignment but represents a command execution surface. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8).
- Ingestion points: Untrusted data enters the context via user-provided "existing brand content" (e.g., website copy, blog posts).
- Boundary markers: None; the instructions do not require the use of delimiters or specific commands to ignore embedded instructions in the brand samples.
- Capability inventory: The skill generates complex TSX components and implements SEO structured data using
dangerouslySetInnerHTML. - Sanitization: None; the skill lacks validation or escaping steps for the brand content before it is processed and used to generate code.
Audit Metadata