humanizer-ar-shami
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted user text for the purpose of dialectal rewriting. 1. Ingestion points: The skill receives user text via the instructions in SKILL.md. 2. Boundary markers: None present; there are no instructions to delimit input or ignore instructions within the text. 3. Capability inventory: Includes Read, Write, Edit, and AskUserQuestion tools. 4. Sanitization: No sanitization or escaping of external content is specified.
- [EXTERNAL_DOWNLOADS]: The skill references an external repository (github.com/blader/humanizer) for linguistic context.
Audit Metadata