customer-experience
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No malicious override or bypass instructions were detected. The skill uses standard instructional language for data generation.
- [Data Exposure & Exfiltration] (SAFE): The skill references local file paths for output (e.g., 'define/관찰결과.md'), which is standard behavior for document generation. No network commands or access to sensitive user credentials were found.
- [Remote Code Execution] (SAFE): No scripts, package installations, or remote download commands (curl/wget) are present in the skill.
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted user input (market research, MVP topics) to generate simulated data. While there are no explicit boundary markers, the skill lacks high-privilege capabilities (like shell execution or network writing), limiting the risk to purely textual output.
- [Persistence & Privilege Escalation] (SAFE): No mechanisms for maintaining access or acquiring elevated permissions were identified.
Audit Metadata