nz-business-english
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied text for drafting and editing, which represents a potential surface for indirect prompt injection.
- Ingestion points: User-provided emails, chat messages, proposals, and other business communications intended for rewriting or tone-checking (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed text.
- Capability inventory: None. The skill does not use network tools, file system writes, or command execution; it is restricted to text transformation.
- Sanitization: No explicit sanitization or filtering of external content is described.
- [NO_CODE]: The skill consists entirely of natural language instructions and markdown examples. It does not include scripts, binaries, or configuration files that could execute logic on the host system.
Audit Metadata