gws-gmail-reply-all

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines usage patterns for the 'gws' CLI tool to interact with Gmail, specifying flags for message identification, email bodies, and file attachments.
  • [INDIRECT_PROMPT_INJECTION]: As the skill is intended to process and respond to external email messages, it possesses an attack surface for indirect prompt injection where malicious content in an email could attempt to subvert the agent's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:42 PM
Security Audit — agent-trust-hub — gws-gmail-reply-all