persona-customer-support
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from customer emails, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads external data from customer emails using the
gws gmail +triagecommand as described inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potentially malicious instructions embedded within the email content.
- Capability inventory: The skill possesses the ability to write to external systems, including appending to spreadsheets (
gws sheets +append), sending messages to Chat spaces for escalation, and creating calendar events (gws calendar +insert) as specified inSKILL.md. - Sanitization: No sanitization, filtering, or validation steps are defined for the content retrieved from emails before it is used in subsequent operations.
Audit Metadata