landing-page
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
REFERENCES.mdfile includes a link to an external resource hosted on GitHub (raw.githubusercontent.com/coreyhaines31/marketingskills). This resource is intended for documentation and structural inspiration rather than executable code. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user data to generate landing page copy.
- Ingestion points: User answers to the "Quick questions" section in
SKILL.md(e.g., offer details, proof points, audience pain points). - Boundary markers: None identified in the prompt instructions to separate user-provided content from agent instructions.
- Capability inventory: The skill is designed to generate text outlines, hero copy, benefit bullets, and FAQ sections based on the input.
- Sanitization: There are no explicit instructions to sanitize or validate user input before it is used in the generation workflow.
Audit Metadata