persona-exec-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from sources such as email inboxes and calendar event descriptions which could contain malicious instructions.
- Ingestion points: The skill reads external data via
gws gmail +triage(email content) andgws workflow +meeting-prep(meeting descriptions and linked documents). - Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between its system instructions and the untrusted data it processes.
- Capability inventory: The skill possesses the ability to send emails (
gws gmail +send), modify calendar events (gws calendar +insert), and interact via chat (gws-chat). - Sanitization: No sanitization, filtering, or validation of the external content is specified in the skill's instructions.
Audit Metadata