gws-workflow-weekly-digest
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 which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests unread email summaries and counts from Gmail, as well as agenda items from Google Calendar weekly schedules.
- Capability inventory: The skill executes the vendor-provided gws CLI tool to fetch and present data to the agent.
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate external data from the agent's core instructions.
- Sanitization: The skill definition does not provide evidence of sanitization or content filtering for the ingested email or calendar data.
Audit Metadata