genpark-marketing-banner-agent-skill
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
genpark-banner-agentpackage and clones a repository from GitHub (alphaparkinc/genpark-marketing-banner-agent-skill). These are third-party resources that are required for the skill's primary functionality but are external to the immediate execution environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from configuration files and CMS API endpoints to automate deployment logic.
- Ingestion points:
config/banners.yamland responses from theBANNER_API_ENDPOINT. - Boundary markers: No explicit boundary markers or instruction-override warnings are provided for interpolated configuration data.
- Capability inventory: The skill performs network operations via
requests, uploads assets to AWS S3 usingS3Deployer, and executes file system operations for image processing via thepillowlibrary. - Sanitization: There is no evidence of validation or sanitization for values retrieved from external configuration or API sources before they are used in deployment logic.
Audit Metadata