coauthoring-docs

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate workflow for document co-authoring. All instructions are procedural and aimed at helping the user refine content through structured iterations.
  • [COMMAND_EXECUTION]: The workflow utilizes standard file system tools (specifically 'the Write tool' and 'the Edit tool') to create and modify document drafts. These operations are transparent, purpose-built for the drafting task, and occur within the agent's controlled environment.
  • [DATA_EXFILTRATION]: The skill integrates with external workspace services (such as Google Drive, Slack, and SharePoint) to gather document context. These interactions rely on established platform connectors and are triggered by explicit user inputs or shared links, representing standard integration behavior rather than unauthorized data access.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 11:03 AM
Security Audit — agent-trust-hub — coauthoring-docs