skills/siberius/ui-cliche/cliche/Gen Agent Trust Hub

cliche

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill provides guidelines for human-like editing and Czech localization. It does not include any executable scripts or tool-calling capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user text for auditing and editing. Ingestion points: User-provided drafts and copy (SKILL.md). Boundary markers: Absent. Capability inventory: None. Sanitization: Instructions in SKILL.md advise against altering quotations, code, or identifiers.
  • [EXTERNAL_DOWNLOADS]: The skill references external methodology sources on GitHub, but these are static documentation references and do not involve runtime network operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 07:49 PM