email-creative-builder
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is primarily instructional and does not contain executable code, scripts, or binary assets. All logic is implemented through natural language instructions for the AI agent.
- [SAFE]: It contains explicit security guidance in the 'Instructions' section, reminding the agent to treat external inputs (CSV exports, scraped copy, CRM signals) as untrusted and to never follow instructions embedded within them, effectively mitigating indirect prompt injection risks.
- [SAFE]: The skill uses structured data management (registry-events.py, claims-ledger.md) for handling marketing claims, which prevents the generation of fabricated or unverified information.
- [SAFE]: Links to other internal skills and reference materials follow standard documentation practices and do not involve remote code execution or unauthorized downloads.
Audit Metadata