persona-exec-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external, untrusted sources, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill retrieves external data through
gws gmail +triage(emails) andgws workflow +meeting-prep(meeting descriptions and attendees) as defined inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions in
SKILL.mdto prevent the agent from following commands embedded within these external data sources. - Capability inventory: The persona has the ability to take actions based on processed data, specifically sending emails (
gws gmail +send) and creating calendar events (gws calendar +insert) inSKILL.md. - Sanitization: No sanitization, filtering, or validation steps are mentioned for the data fetched from external workflows.
Audit Metadata