pyqt6-ui-development-rules
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential risk surface for indirect prompt injection by processing external untrusted files while maintaining extensive capabilities.\n
- Ingestion points: Processes local python/GUI files via configured globs (
**/gui/**/*.*,**/*_ui.py,**/*_dialog.py,**/*_window.py) inSKILL.md.\n - Boundary markers: Absent; no prompt isolation boundaries or specific exclusion rules are provided to protect the agent from embedded prompt instructions inside comments or UI text within files.\n
- Capability inventory: Allowed tools include
Write,Edit, andBashas declared inSKILL.mdfrontmatter.\n - Sanitization: Absent; file ingestion lacks content filtering, pre-parsing sanitization, or validation routines to separate structural data from text commands.
Audit Metadata