genpark-marketing-banner-agent-skill

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include cloning a repository from github.com/alphaparkinc and installing the genpark-banner-agent package. These resources are provided by the specific vendor for the skill's functionality.
  • [PROMPT_INJECTION]: The skill handles data from external configuration files (config/banners.yaml) and API endpoints (BANNER_API_ENDPOINT) which could serve as vectors for indirect prompt injection. Ingestion points: Reads campaign data and layout definitions from YAML files and API responses. Boundary markers: None identified in the provided instructions or code snippets. Capability inventory: Perform network API requests (APIDeployer), S3 uploads (S3Deployer), and image modification/saving (BannerMatcher). Sanitization: No input validation or filtering is shown for data retrieved from external configuration or network sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:35 AM
Security Audit — agent-trust-hub — genpark-marketing-banner-agent-skill