internal-email-composer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions found that attempt to bypass safety filters or override agent behavior.
  • [Data Exposure & Exfiltration] (SAFE): No access to sensitive file paths, hardcoded credentials, or network operations detected.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not include any external package installations or remote script executions.
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted user input to generate email content, creating a potential surface for indirect injection.
  • Ingestion points: User-provided context and goals for email generation.
  • Boundary markers: Absent.
  • Capability inventory: The skill is limited to text generation; it lacks the ability to execute commands, write files, or make network calls.
  • Sanitization: No specific sanitization or filtering of input data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM