qt-devtools-app-interaction
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of the
qt-ai-dev-toolscommand-line utility to perform UI automation tasks such as widget inspection, clicking, and text entry. - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it reads data from external application UIs.
- Ingestion points: Data is ingested through widget names, labels, and text content via commands like
tree,text,state, andfind(SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data read from the UI.
- Capability inventory: The agent has capabilities to perform UI interactions (
click,fill,type,key), take screenshots (screenshot), and potentially execute Python code (mentioned via the related skillqt-devtools-runtime-eval). - Sanitization: There are no explicit sanitization or validation steps described for handling text read from external widgets before it is processed by the agent.
Audit Metadata