persona-content-creator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a persona that interacts with and processes content from external data sources (Google Docs, Drive, and Sheets).
- Ingestion points: Processes data through commands like
gws docs +writeandgws drive files listin SKILL.md. - Boundary markers: There are no explicit instructions to the agent to distinguish between its instructions and content found within processed documents.
- Capability inventory: The skill utilizes capabilities for document modification (
docs +write), file uploads (drive +upload), and communication via email (gmail +send) and chat. - Sanitization: The instructions do not specify any validation or sanitization routines for content ingested from Workspace files.
Audit Metadata