gws-events-subscribe

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a way to ingest external data from Google Workspace resources which represents a potential attack surface for indirect instructions.
  • Ingestion points: Event data retrieved from Google Workspace resource URIs (e.g., chat.googleapis.com) through Pub/Sub streaming.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are defined within the skill instructions for the resulting data stream.
  • Capability inventory: Command execution of the gws utility and file system write capabilities via the --output-dir flag.
  • Sanitization: The skill does not describe specific sanitization or filtering routines for the ingested event content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 12:40 PM