bggg-tiktok-search
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/tk_real_chrome.pyutilizessubprocess.check_outputto executeosascriptcommands. This is a legitimate mechanism on macOS to control the local Google Chrome application for navigation and data extraction via JavaScript injection. - [COMMAND_EXECUTION]: The script
scripts/tk_research.pyemploys the Playwright library to connect to a running Chrome instance via the Chrome DevTools Protocol (CDP). This allows the skill to automate research tasks while inheriting the user's active session and security context. - [SAFE]: The skill processes untrusted content such as TikTok video titles and user bios during its extraction process. While this represents a potential surface for indirect prompt injection, the risk is categorized as low since the data is structured into local reports (JSON/CSV) and the skill explicitly focuses on read-only research activities without performing sensitive automated actions based on the ingested content.
Audit Metadata