huashu-article-to-x
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions found that attempt to bypass AI safety filters or override system prompts.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network requests detected.
- [Remote Code Execution] (SAFE): No external dependencies or remote script downloads are present. The skill contains only markdown-based instructions.
- [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted user-provided articles (3000-5000 words). While it lacks explicit boundary markers or sanitization logic, its capabilities are strictly limited to text transformation, posing no significant technical risk.
- Ingestion points: User-provided articles via prompt input.
- Boundary markers: Absent.
- Capability inventory: Text summarization and formatting; no system-level capabilities detected.
- Sanitization: Absent.
Audit Metadata