aeo-audit
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill reads from application-specific local directories (
~/.claude-marketing/) to load brand context and standard operating procedures (SOPs). This file access is localized to the application's domain and is intended for brand-consistent analysis. - [SAFE]: There are no indicators of data exfiltration, credential harvesting, or unauthorized network activity. All network-related analysis (citation checking, visibility analysis) is performed using the agent's inherent search capabilities.
- [SAFE]: No obfuscation, remote code execution, or persistence mechanisms were detected. The instructions follow a transparent process for data collection and reporting.
- [SAFE]: The skill processes local configuration files (profiles, guidelines, SOPs) which represent an indirect prompt injection surface. However, as these files are part of the local brand management infrastructure, the risk is minimal and consistent with the skill's purpose.
Audit Metadata