skills/reason-machines/marketing-skills/marketing-pipeline-share-content-automation/Gen Agent Trust Hub
marketing-pipeline-share-content-automation
Warn
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to clone a repository from
https://github.com/pennydinh/marketing-pineline-share.git. This repository is not from a known trusted organization or the skill author's verified infrastructure. - [REMOTE_CODE_EXECUTION]: The installation steps include running
npm install,yarn install, orpnpm installwithin the cloned directory. This action allows the execution of arbitrary lifecycle scripts defined in the external repository'spackage.jsonfile. - [COMMAND_EXECUTION]: The skill suggests using CLI commands such as
npx content-pipelineandnpm run remotionwhich rely on the code downloaded from the unverified external repository. - [INDIRECT_PROMPT_INJECTION]: The research module is designed to crawl news and social media content from platforms like TechCrunch and Twitter, passing the raw data directly to AI models for analysis. This creates a surface where malicious instructions hidden in processed web content could manipulate the agent's behavior.
- Ingestion points:
lib/research/scraper.ts(processes external web data). - Boundary markers: None identified in the provided code snippets.
- Capability inventory: Network operations for scraping and AI model invocation.
- Sanitization: No visible sanitization or filtering logic is present in the research or analysis code snippets.
Audit Metadata