email-security

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown and checklists. No executable scripts, network operations, or sensitive data access patterns were detected.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data (email samples), which constitutes a surface for indirect prompt injection.
  • Ingestion points: Raw email headers and content are ingested into the agent context for analysis.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded content are defined.
  • Capability inventory: No automated script execution or dangerous tool usage is defined within the skill files.
  • Sanitization: No explicit validation or filtering steps for untrusted email content are provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 08:15 AM
Security Audit — agent-trust-hub — email-security