gws-multi-account

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface Detection
  • Ingestion points: The skill reads untrusted data from external sources via google_gmail (emails) and google_calendar (events).
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content within the retrieved data.
  • Capability inventory: The skill has the capability to perform write operations including sending/replying to emails (google_gmail) and creating/updating events (google_calendar).
  • Sanitization: No explicit sanitization or validation of the content retrieved from Google Workspace is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 02:59 AM