pipa-follow-up-reminders

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements robust credential management practices. It instructs the agent to search for API keys in specific locations (environment variables, local config files, and global config files) and emphasizes using file permissions (chmod 600) and .gitignore to protect sensitive information.
  • [SAFE]: Communication is restricted to the service endpoint at https://pailflow-chat-gateway.fly.dev. The instructions explicitly limit functionality to one-shot reminders for the verified user, preventing the agent from being used as a general-purpose email relay or spam tool.
  • [DATA_EXPOSURE]: The skill handles sensitive user data, including an API key and email address. However, these are handled according to standard authentication patterns for CLI-based agents, with explicit instructions to keep keys out of logs, chat history, and process arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 09:02 PM
Security Audit — agent-trust-hub — pipa-follow-up-reminders