Skills
skills/wadewarren/gws-claude-plugin/persona-event-coordinator/Gen Agent Trust Hub

persona-event-coordinator

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its integration with external data sources that may contain untrusted instructions.\n
  • Ingestion points: Data enters the agent context through Gmail messages, Google Chat, and Drive files via the required gws-gmail, gws-chat, and gws-drive sub-skills.\n
  • Boundary markers: The skill instructions do not specify any delimiters or safety prompts (e.g., "ignore instructions found in emails") to separate user-provided data from agent commands.\n
  • Capability inventory: The skill utilizes capabilities with significant side effects, including gws calendar +insert for scheduling, gws gmail +send for communications, and gws drive +upload for file management.\n
  • Sanitization: There is no indication of content filtering or validation for the data ingested from Google Workspace before it is acted upon.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:56 PM