doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to ingest and process information from external sources like shared documents and messaging platforms.
  • Ingestion points: Context is gathered from shared document links, user-uploaded files, and messaging channels such as Slack and Teams via integrations.
  • Boundary markers: The instructions do not specify the use of delimiters or ignore instructions when processing content from these external sources.
  • Capability inventory: The skill utilizes create_file and str_replace tools to write and edit the final documentation.
  • Sanitization: No explicit sanitization or validation logic is defined for the content fetched from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill fetches context and documentation configuration from official integrations and shared links upon user request.
  • Evidence: The skill coordinates with Slack, Teams, Google Drive, and SharePoint to pull relevant project context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 04:40 PM