baoyu-post-to-x
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local TypeScript scripts (
x-browser.ts,x-video.ts,x-article.ts) using thenpx -y buncommand to automate browser interactions via Chrome DevTools Protocol (CDP). This is the intended primary function for bypassing anti-automation measures on X. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it processes external Markdown files and user-provided text to generate public posts.
- Ingestion points: Markdown file paths and positional text arguments in
x-article.tsandx-browser.ts. - Boundary markers: Absent; there are no specific instructions or delimiters mentioned to prevent the agent from following instructions embedded within the content it is asked to post.
- Capability inventory: The skill can read local files, control a web browser, and publish content to a public social media platform.
- Sanitization: No evidence of content sanitization or validation of the input files is provided in the skill instructions.
Audit Metadata