outlook-pre-onboarding-checklist-meeting

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is configured to ingest and process data from an external source (Docusign workflow context) to perform automated actions, which may present a surface for indirect influence if the source data is manipulated.
  • Ingestion points: Data such as 'Employee Full Name' and agreement 'Effective Date' enter the agent's context through the Docusign workflow trigger in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the interpolated data, which is a common practice to help delineate untrusted content.
  • Capability inventory: The skill utilizes the Work IQ Calendar (Preview) tool to create calendar events, demonstrating a capability to act on the processed data.
  • Sanitization: There are no explicit instructions for validating or escaping the 'Employee Full Name' string before it is incorporated into the meeting subject.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 09:54 PM