x-posting
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes the
mcp__claude-in-chrometoolset to perform browser-based automation on a legitimate well-known service (x.com). - [SAFE]: No signs of malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
- [SAFE]: The instructions explicitly include safety protocols, requiring the agent to confirm tweet content with the user before finalizing the post.
Audit Metadata