conducting-customer-research

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill consists entirely of Markdown documentation. No scripts (.py, .js, .sh), binaries, or configuration files that execute commands were found in the skill package.
  • [Indirect Prompt Injection] (SAFE): The workflow describes ingesting untrusted data such as community forum discussions and customer reviews (found in workflow.md). While this creates a surface for indirect prompt injection, the lack of associated executable code or automated system capabilities within the skill makes functional exploitation impossible.
  • [Data Exposure] (SAFE): The workflow mentions handling sensitive CRM data and customer information. However, the skill only defines a process for humans or agents to follow and does not include any automated exfiltration mechanisms, hardcoded credentials, or unauthorized access patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 02:15 AM