doc-coauthoring
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
create_fileto generate document templates andstr_replaceto perform surgical edits on drafted content. - [EXTERNAL_DOWNLOADS]: It pulls context from well-known services like Google Drive, Slack, Teams, and SharePoint to inform the writing process.
- [PROMPT_INJECTION]: The skill processes untrusted external data, creating a surface for indirect prompt injection.
- Ingestion points: Shared documents, message history, and project files.
- Boundary markers: Absent; the skill does not define specific isolation markers for external content.
- Capability inventory: File writing (
create_file,str_replace) and authenticated network reading via integrations. - Sanitization: No sanitization of ingested data is described in the workflow.
Audit Metadata