Audience Persona Builder
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill instructions focus on legitimate data gathering for marketing purposes.
- [PROMPT_INJECTION]: The skill processes untrusted external data, creating a surface for indirect prompt injection. Ingestion points: Untrusted content enters the agent context via WebFetch (analyzing the business URL) and WebSearch (gathering reviews and research). Boundary markers: Explicit delimiters for fetched content are absent. Capability inventory: Uses WebFetch, WebSearch, and local file-write (ADS-AUDIENCE.md). Sanitization: No specific sanitization of external content is defined.
Audit Metadata