gws-gmail-triage
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from a user's Gmail inbox, which exposes the agent to indirect prompt injection.
- Ingestion points: Incoming email details (sender, subject, date) are read into the agent context via the
gws gmail +triagecommand inSKILL.md. - Boundary markers: Absent. There are no explicit delimiters or rules defined to instruct the agent to ignore instructions embedded within the email subjects or headers.
- Capability inventory: Executes the
gwscommand-line utility as specified inSKILL.md. - Sanitization: Absent. The data from the mailbox is displayed without structural escaping or filtering against prompt injection techniques.
Audit Metadata