email-check

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted email content, creating a vulnerability surface for indirect prompt injection where malicious emails could influence the triage results or generated replies.
  • Ingestion points: Email subjects and bodies fetched from Gmail or Outlook (SKILL.md).
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used to separate untrusted data from the agent's logic.
  • Capability inventory: The skill uses Read, Grep, and Glob for local file access and utilizes dedicated MCP tools for email access. No arbitrary command execution or external network capabilities are listed.
  • Sanitization: The skill lacks sanitization for email body content before processing it for keywords or context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 09:41 PM