doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill references a repository owned by a trusted organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of content from external sources, such as Slack, Microsoft Teams, Google Drive, and SharePoint, to provide context for document drafting. This creates a surface where the agent might process untrusted data containing embedded instructions.
  • Ingestion points: Integration points with team messaging channels and shared document repositories described in SKILL.md under the Context Gathering stage.
  • Boundary markers: The instructions do not specify the use of delimiters or clear separation between system instructions and data fetched from external integrations.
  • Capability inventory: The workflow employs file creation and editing tools (create_file, str_replace) and can invoke sub-agents for reader testing.
  • Sanitization: No sanitization, filtering, or validation logic is defined for the content retrieved from external integrations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:45 PM
Security Audit — agent-trust-hub — doc-coauthoring