persona-team-lead
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest and process potentially untrusted data from external communication and storage platforms.
- Ingestion points: Data enters the agent's context through
gws-gmail(emails),gws-calendar(event details),gws-drive(document content), andgws-sheets(spreadsheet data). - Boundary markers: The instructions lack explicit boundary markers or instructions to ignore embedded commands when the agent reads external content.
- Capability inventory: The skill allows the agent to perform actions based on this data, such as creating messages in chat spaces (
gws-chat), sending emails (gws-gmail), and updating spreadsheets (gws-sheets). - Sanitization: Although the skill documentation suggests using a
--sanitizeflag for sensitive team data, this is a procedural tip for the user rather than a programmatic defense against malicious instructions hidden in the processed data.
Audit Metadata