onboarding-cro

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely advisory and focuses on providing frameworks, principles, and experiment ideas for user onboarding optimization.
  • [REMOTE_CODE_EXECUTION]: No remote scripts, package installations, or dynamic code execution patterns were found in any of the files.
  • [DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive system files. It only reads specific project context files (.agents/product-marketing-context.md) which is a standard pattern for context-aware agents.
  • [PROMPT_INJECTION]: No malicious instructions aimed at bypassing AI safety filters or overriding system behavior were detected.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from product marketing context files, it lacks any dangerous capabilities (such as file-writing, network access, or command execution) that could be exploited through malicious content in those files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:24 AM
Security Audit — agent-trust-hub — onboarding-cro