ai-content-humaniser
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides purely instructional content focused on content humanisation and cultural localisation for the East African market. No malicious patterns, obfuscation, or unauthorized data access were found.
- [NO_CODE]: This skill consists entirely of natural language instructions in markdown format and does not include any scripts, binaries, or automated tools.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to process untrusted AI-generated drafts (Ingestion point: SKILL.md). While boundary markers and explicit sanitisation are absent, the skill's capability inventory is empty (no file system access, network operations, or tool execution), which prevents an injection from causing side effects or exfiltration. The instructions focus on critical analysis and rewriting of the input data.
Audit Metadata