marketing-pipeline-auto-content
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's installation instructions include cloning a repository from an external GitHub account:
https://github.com/pennydinh/marketing-pineline-share.git. This is a primary function of the skill to provide the template code. - [INDIRECT_PROMPT_INJECTION]: The skill includes a research module that crawls data from external platforms (TechCrunch, Twitter, a16z) and interpolates this content into prompts for Claude and OpenAI. While it uses
JSON.stringifyto format the data, it lacks explicit boundary markers or instructions for the AI to ignore potential instructions embedded in the crawled content. - [DYNAMIC_EXECUTION]: The project utilizes the Remotion library (
@remotion/bundlerand@remotion/renderer) to programmatically bundle and render video compositions at runtime based on generated content. - [COMMAND_EXECUTION]: The instructions involve standard development commands such as
git clone,npm install, andnpm run devto set up and run the marketing pipeline project.
Audit Metadata