human-voice-writer
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions and reference materials. There are no scripts, binaries, or configuration files that execute commands or interact with the host system or file system.- [SAFE]: No network activity or external communication patterns were detected. The skill does not attempt to fetch external resources, download code, or exfiltrate any data.- [SAFE]: No prompt injection or safety bypass patterns were identified. While the instructions use strong language such as "Ban" or "Never use," these are strictly limited to stylistic writing guidelines and vocabulary control.- [SAFE]: No obfuscation, hidden characters, homoglyphs, or deceptive metadata were found in any of the skill files. All content is human-readable and transparent.- [SAFE]: Although the skill processes user-provided text for humanization, it lacks any functional capabilities (such as network or shell access) that would create a vulnerability surface for indirect prompt injection.
Audit Metadata