Skills
skills/reggiechan74/claude-plugins/authenticate/Gen Agent Trust Hub

authenticate

Warn

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill interacts with sensitive file paths intended for storing OAuth keys and credentials, specifically ~/.gmail-mcp/gcp-oauth.keys.json, ~/.calendar-mcp/gcp-oauth.keys.json, and the generated credentials.json files. Accessing these types of files is sensitive as they contain access tokens and client secrets.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to create directories (mkdir), list files (ls), and run authentication logic via Node.js (node). It also provides a troubleshooting command to kill processes (lsof and kill -9) associated with specific network ports.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 16, 2026, 12:01 AM
Security Audit — agent-trust-hub — authenticate