doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from various sources to inform its writing process.
  • Ingestion points: The workflow involves reading content from shared documents (Google Drive, SharePoint), messaging channels (Slack, Teams), and local files provided by the user.
  • Boundary markers: There are no instructions for the agent to utilize delimiters or specific boundary markers when processing these external data sources to prevent them from influencing the agent's behavior.
  • Capability inventory: The skill has the ability to create and modify files in the environment using create_file and str_replace tools, and it can perform searches across connected organizational platforms.
  • Sanitization: The skill does not implement any sanitization or validation of the fetched external content before using it to draft document sections.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from external collaboration and cloud storage platforms.
  • It leverages integrations to fetch information from well-known services including Slack, Microsoft Teams, Google Drive, and SharePoint to gather document context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 04:38 PM
Security Audit — agent-trust-hub — doc-coauthoring