marketing-pipeline-content-automation
Warn
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation instructs the user to clone a repository from an untrusted third-party source:
https://github.com/pennydinh/marketing-pineline-share.git. - [REMOTE_CODE_EXECUTION]: Running code from the cloned repository represents execution of remote, unverifiable content. The skill also uses
@remotion/bundlerto dynamically compile and execute project code during video rendering. - [COMMAND_EXECUTION]: Setup involves shell commands like
npm installandnpm run dev, which execute scripts and code from the untrusted external repository. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8). 1. Ingestion points: Data is fetched from news sites (TechCrunch, Twitter) in
lib/research/scanner.ts. 2. Boundary markers: None; external data is interpolated directly into prompts (e.g.,${request.research}). 3. Capability inventory: Performs network requests to AI APIs and media rendering via subprocesses. 4. Sanitization: No validation or filtering is applied to the aggregated research data.
Audit Metadata