marketing-pipeline-share-ai-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 instructs the agent to clone a repository from an untrusted third-party source (
https://github.com/pennydinh/marketing-pineline-share.git) and install its dependencies. This executes unverifiable external code in the host environment. - [INDIRECT_PROMPT_INJECTION]: The skill scrapes data from TechCrunch, Twitter, and LinkedIn and directly interpolates it into prompts for Claude and OpenAI. There are no boundary markers or sanitization steps to prevent malicious data from these sources from injecting instructions into the model's context.
- [DYNAMIC_EXECUTION]: The video generation process uses the Remotion library to bundle and execute local code at runtime. This dynamic execution of scripts within the cloned repository represents a potential security risk if the repository content is untrustworthy.
Audit Metadata