gws-gmail-triage

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were identified in the skill definition.
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified. Ingestion points: Gmail sender names and subject lines from unread messages. Boundary markers: No output delimiters are specified. Capability inventory: The gws CLI tool is required. Sanitization: No sanitization is performed on the ingested data within the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:56 PM