form-cro

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected in the skill instructions, metadata, or evaluation files. The skill's primary purpose is to provide advice on improving web form completion rates.
  • [SAFE]: The skill mentions reading a context file (.agents/product-marketing-context.md) to inform its recommendations. While this represents a data ingestion surface, the skill does not possess any dangerous capabilities (such as code execution or network operations) that could be exploited via indirect prompt injection from this file.
  • [SAFE]: All external services mentioned (e.g., Clearbit, reCAPTCHA) are referenced as advice for the user to implement on their own forms, rather than being tools invoked by the agent itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:54 PM