ms365
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from external emails, creating a surface for indirect prompt injection.
- Ingestion points: The
scripts/src/email.tsscript fetches email subjects and full message bodies from the Microsoft Graph API. - Boundary markers: The retrieved data is output as raw JSON without specific delimiters or warnings to the agent to ignore embedded instructions.
- Capability inventory: The skill is configured with
Bash(node:*)permissions to execute its internal logic. - Sanitization: No sanitization or filtering of the retrieved email content is performed before it is passed to the agent's context.
Audit Metadata