klarsprak
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions focused on linguistic quality, Norwegian grammar, and professional writing style. It does not request access to sensitive files, perform network operations, or execute shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (e.g., READMEs, ADRs, UI text) without explicit boundary markers or sanitization instructions. However, because the skill has no dangerous capabilities (no file system writes, no network access, no code execution), the risk of exploiting this surface is negligible. The skill is limited to text transformation.
Audit Metadata