cali-social-engage
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Python scripts (
scripts/draft_reply.pyandscripts/post_x_reply.py) to manage social media interactions. - These scripts perform legitimate functions such as reading local JSON data (
data/ranked.json) and automating browser interactions for X (formerly Twitter) using Playwright. - The automation on X is designed with security in mind: it requires a pre-existing session file (
~/.social-listening/x-state.json), launches a visible browser window (headless=False), and explicitly requires the user to click the final 'Reply' button manually, preventing automated spam or unintended posts.
Audit Metadata