baoyu-danger-x-to-markdown
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local TypeScript files using the
bunruntime or vianpxif bun is not installed. - [EXTERNAL_DOWNLOADS]: Fetches media assets (images and videos) from X's content delivery networks (
pbs.twimg.com,video.twimg.com) to store them locally when the--download-mediaflag is used. - [EXTERNAL_DOWNLOADS]: May use
npxto download thebunexecution environment if it is missing from the system. - [SAFE]: Contains a hardcoded bearer token in
scripts/constants.ts, which is identified as the well-known public guest token for X's API and does not represent a credential leak. - [SAFE]: Implements a transparent consent mechanism that requires the user to acknowledge the risks of using a reverse-engineered API before the tool becomes operational.
- [SAFE]: Utilizes Chrome DevTools Protocol (CDP) to capture authentication cookies from a browser session to enable scraping of authenticated content. These cookies are stored locally in the user's data directory for session persistence.
- [PROMPT_INJECTION]: As the skill ingests and processes untrusted content from X (tweets and articles), an indirect prompt injection surface exists. Malicious content could be crafted to influence an agent's behavior when it later reads the generated markdown files.
Audit Metadata