client-voice-mapping
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No executable code, scripts, or binary files were found in the skill. The content is entirely composed of instructional markdown for copywriting tasks.
- [PROMPT_INJECTION]: The skill is designed to analyze user-provided text samples for brand voice extraction. This constitutes a surface for indirect prompt injection; however, because the skill does not have any tool-use capabilities (e.g., file system access or network requests), this surface is considered benign.
- Ingestion points: User-provided sample copy (SKILL.md)
- Boundary markers: None provided in the instructions
- Capability inventory: No tool-use or system commands identified
- Sanitization: No input validation or escaping mechanisms
- [DATA_EXFILTRATION]: The skill includes a static link to an external professional resource website (theaicareerlab.com). This is an informational reference provided for the user and does not represent an automated exfiltration vector.
Audit Metadata