mini-ai-marketing-agency-generator
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to clone a project from a third-party GitHub repository (https://github.com/rover-aungkhine/mini-ai-marketing-agency.git). This repository is the source of the code which is then executed locally via a web browser or a local Python server.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests untrusted user data (such as business names and product descriptions) and interpolates it into templates. The logic provided in
SKILL.mdlacks sanitization, creating an attack surface where malicious input could influence the output. - Ingestion points: User-provided fields including
businessName,businessType,product,audience, andofferdefined in theformFieldsobject inSKILL.md. - Boundary markers: None; placeholders (e.g.,
{name},{product}) are replaced using global string substitution (.replace()) without delimiters or instructions to ignore embedded commands. - Capability inventory: The script uses
navigator.clipboard.writeTextfor clipboard access and performs DOM manipulation to display results. - Sanitization: None; the
interpolatefunction performs direct replacement without escaping or validating the content of the context variables.
Audit Metadata