sales-investor-emails-skill

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for generating email content based on user-provided or CRM context. No prompt injection, role-play overrides, or safety bypass patterns were detected.
  • [SAFE]: Data access is limited to reading CRM contact notes and company positioning files (e.g., context/company.md) to facilitate email drafting. No hardcoded credentials, sensitive system file access, or unauthorized network exfiltration patterns were found.
  • [SAFE]: There are no executable scripts, remote downloads, or dynamic code execution patterns included in the skill. The functionality is purely text-based and instruction-driven.
  • [SAFE]: The skill ingests data from external sources (CRM tool outputs). While this represents a surface for indirect prompt injection, the agent's actions are restricted to text generation, posing no risk of command execution or privilege escalation based on the untrusted input.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 11:24 PM
Security Audit — agent-trust-hub — sales-investor-emails-skill