skills/clawlink-hq/skills/gmail/Gen Agent Trust Hub

gmail

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the @useclawlink/cli package via npx. This is the official command-line tool provided by the vendor to interface with their integration service.
  • [COMMAND_EXECUTION]: Shell commands are employed to authenticate the user and execute Gmail-specific actions through the vendor CLI.
  • [CREDENTIALS_UNSAFE]: The skill mentions that authentication credentials are stored locally in the user's home directory (~/.clawlink/credentials.json). This is a standard practice for CLI-based authentication and no sensitive keys are hardcoded within the skill itself.
  • [DATA_EXFILTRATION]: The skill is designed to read and process email data. It includes a specific safety instruction requiring the agent to confirm with the user before performing any write operations, which serves as a mitigation against automated or unintended actions triggered by untrusted email content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 11:34 AM
Security Audit — agent-trust-hub — gmail