persona-sales-ops
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest untrusted data from external sources, which could potentially harbor malicious instructions.
- Ingestion points: Processes data from emails (
gws-gmail) and calendar events (gws-calendar) as specified in the SKILL.md instructions. - Boundary markers: There are no explicit delimiters or warnings to ignore instructions embedded within the external data.
- Capability inventory: The skill utilizes tools for file and data modification, including
gws sheets +appendandgws drive +upload. - Sanitization: No content validation or escaping mechanisms are specified in the instructions for handling the data retrieved from external services.
Audit Metadata