qt6-desktop-ux
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to query external documentation via the Context7 MCP tool, creating a potential surface for indirect prompt injection from retrieved external data.\n
- Ingestion points:
mcp__context7__query-docstool output.\n - Boundary markers: None specified to differentiate data from instructions.\n
- Capability inventory: C++ code generation and project management.\n
- Sanitization: No sanitization mechanisms are described for tool outputs.\n- [DYNAMIC_EXECUTION]: The skill contains a shell command example to execute a local Python script for theme color management.\n
- Evidence:
python scripts/add_theme_color.py colorName \"#darkHex\" \"#lightHex\" -d \"description\" -s.\n - Context: This represents a vendor-owned utility for development automation.
Audit Metadata