human-tone
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No malicious behavior, obfuscated commands, or unauthorized data access patterns were detected. The skill instructions are entirely focused on stylistic text transformation.
- [NO_CODE]: The skill consists exclusively of Markdown files and natural language instructions. There are no scripts, binaries, or platform-level tool definitions provided.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text, which is an inherent attack surface for indirect prompt injection. 1. Ingestion points: User-supplied marketing copy for humanization (SKILL.md). 2. Boundary markers: Absent (no specific delimiters for input text are defined in the prompt). 3. Capability inventory: None (the skill has no access to shell, network, or file system tools). 4. Sanitization: None.
- [EXTERNAL_DOWNLOADS]: The README provides installation instructions referencing the author's official GitHub repository (Varnan-Tech/opendirectory) and standard distribution platforms.
Audit Metadata