persona-event-coordinator

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill coordinates actions across Google Workspace tools, creating a surface where untrusted data from emails, calendar invites, or spreadsheets could influence agent behavior.
  • Ingestion points: Processes data through gws calendar, gws gmail, and gws sheets as specified in the instructions in SKILL.md.
  • Boundary markers: No explicit instructions are provided to the agent to treat external data as untrusted or to use delimiters when processing event details.
  • Capability inventory: The skill utilizes tools for sending emails (gws gmail +send), posting to chat (gws workflow +file-announce), and uploading files (gws drive +upload), providing a path for potential exfiltration or phishing if the agent is compromised by malicious input.
  • Sanitization: There are no instructions for sanitizing or validating input from external sources before use in downstream operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 09:00 PM