korean-clarity
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill provides instructions for semantic refinement of Korean text. No malicious patterns, obfuscation, or sensitive data access were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill revises Korean text provided by users or agents. 1. Ingestion points: User-supplied or agent-generated Korean text analyzed in SKILL.md. 2. Boundary markers: Explicit instructions to treat quoted passages as data and protect code, URLs, and technical terms from alteration. 3. Capability inventory: The skill possesses no capabilities for network access, file system modification, or command execution. 4. Sanitization: Instructions prohibit inventing new facts or context during the revision process.
- [NO_CODE]: The skill consists entirely of markdown instructions and lacks any executable scripts or binary files.
Audit Metadata