agency-socials
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses AppleScript via
osascriptto save images from the system clipboard to the user's desktop directory for inclusion in generated assets. - [COMMAND_EXECUTION]: Executes a Node.js script using the Playwright library to render HTML templates into image files.
- [EXTERNAL_DOWNLOADS]: Fetches typography assets from trusted and well-known services including Google Fonts and the JSDelivr CDN.
- [PROMPT_INJECTION]: The skill ingests untrusted user input (speaker names, headlines) and interpolates it into HTML templates. This creates a surface for indirect prompt injection, as no boundary markers or sanitization steps are defined for the process. The skill possesses capabilities for file-writing and shell execution which could be influenced by malicious input during the rendering stage.
Audit Metadata