shunk031-humanizer-ja

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Japanese text for rewriting, which presents a surface for indirect prompt injection. 1. Ingestion points: User-provided text processed as per the main workflow in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill only generates text within the LLM context and lacks capabilities for file system access, network operations, or command execution. 4. Sanitization: Absent. The potential impact is minimal because the agent's capabilities are restricted to text output.
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes informational links to two GitHub repositories (gonta223/humanizer-ja and blader/humanizer). These are referenced as conceptual inspirations and do not involve automated downloading or execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:14 PM
Security Audit — agent-trust-hub — shunk031-humanizer-ja