Skills
skills/dglowacki/mega-agent-v2/email-templates/Gen Agent Trust Hub

email-templates

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to the lack of input sanitization in its template rendering logic.
  • Ingestion points: Data is ingested from external JSON files specified via the --data argument in the scripts/format_email.py and scripts/render_template.py scripts.
  • Boundary markers: No boundary markers or special instructions are used within the templates or the rendering script to distinguish between data and potentially malicious instructions.
  • Capability inventory: The scripts/format_email.py script includes the capability to send rendered HTML emails via a GmailClient integration.
  • Sanitization: The render_template function in scripts/render_template.py performs simple string replacement without HTML escaping or input validation, allowing potentially malicious scripts or links to be rendered and sent if the source data is compromised.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 02:24 AM