qt-qml-review
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Python linter script (
references/lint-scripts/qt_qml_lint.py) and the system toolqmllintto analyze project files.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided QML source code as input for multiple analysis agents, creating a surface for indirect prompt injection.\n - Ingestion points: QML files identified through directory globbing or
git diff(SKILL.md).\n - Boundary markers: Instructions for parallel subagents do not specify the use of delimiters or warnings to ignore code-embedded instructions (SKILL.md).\n
- Capability inventory: The skill environment permits file system reads and shell execution of local scripts and git (SKILL.md).\n
- Sanitization: No evidence of sanitization or filtering of the source code content before processing (SKILL.md, qt_qml_lint.py).
Audit Metadata