status-report-drafter-scott-margetts

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external content, such as email threads and call notes, which creates an attack surface for indirect prompt injection.
  • Ingestion points: The skill ingests raw text from pasted emails, call notes, and Teams messages, as well as content from uploaded Excel and Word files (SKILL.md).
  • Boundary markers: There are no instructions to use specific delimiters or to explicitly ignore embedded instructions within the processed data sources.
  • Capability inventory: The skill possesses the ability to search across a user's Microsoft 365 environment (Outlook, SharePoint, Teams) and can draft follow-up emails (SKILL.md).
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the external content before it is incorporated into the agent's reasoning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 08:34 PM
Security Audit — agent-trust-hub — status-report-drafter-scott-margetts