skills/googleworkspace/cli/gws-gmail/Gen Agent Trust Hub

gws-gmail

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious code, obfuscation, or unauthorized data exfiltration patterns were detected.
  • [COMMAND_EXECUTION]: The skill uses the 'gws' binary to interact with the Gmail API, which is consistent with the 'googleworkspace' author context and intended functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface to read and triage external email data, which represents an indirect prompt injection surface.
  • Ingestion points: Gmail message bodies and headers retrieved via helper commands (SKILL.md).
  • Boundary markers: Not defined in this file.
  • Capability inventory: Command execution via the 'gws' binary for Gmail API operations (SKILL.md).
  • Sanitization: None described in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:42 PM
Security Audit — agent-trust-hub — gws-gmail