translate-to-non-native
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious instructions, commands, or obfuscated code were found. The skill is purely prompt-based and operates without any tools or system access.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user text (SKILL.md) for translation. While it lacks explicit boundary markers or sanitization, the risk is negligible as there are no tools, file system writes, or network operations available for exploitation.
Audit Metadata