iblai-marketing-onboarding-cro
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill instructions or supporting files. Analysis covered prompt injection, data exfiltration, remote code execution, and persistence mechanisms.
- [PROMPT_INJECTION]: The instructions do not contain any bypass attempts or overrides of system instructions. The terminology used for marking steps as critical relates to marketing best practices and not safety filter avoidance.
- [DATA_EXFILTRATION]: No network tools (curl, wget) or hardcoded secrets were found. The skill suggests reading marketing context files located in
.agents/or.claude/directories, which are standard for project-specific grounding. - [REMOTE_CODE_EXECUTION]: The skill consists entirely of Markdown and JSON configuration. No script execution, package installation, or dynamic code generation patterns were detected.
Audit Metadata