customer-persona-builder
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is primarily composed of markdown templates and instructions for organizing marketing data. It does not include any scripts, executables, or third-party dependencies that could introduce risk.- [INDIRECT_PROMPT_INJECTION]: The skill processes external input regarding products and markets via arguments to the persona-building workflow. While it possesses the capability to write to the file system using allowed tools, the ingestion of data occurs within a controlled marketing context with no evidence of dangerous command execution or remote data exfiltration. Evidence: Ingestion points are the argument-hints in
SKILL.md; boundary markers are absent; capabilities are limited toReadandWritetools; sanitization is not explicitly defined.
Audit Metadata