qt-devtools-form-and-input

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the qt-ai-dev-tools command-line utility to perform UI automation tasks such as clicking, typing, and managing modal dialogs. It also relies on standard system utilities xsel and xclip for clipboard operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for reading data from untrusted sources, which could influence the agent's subsequent behavior if not properly handled.
  • Ingestion points: The agent is instructed to use clipboard read to ingest content from the system clipboard and text or tree commands to read content directly from the target application's user interface, as documented in SKILL.md.
  • Boundary markers: The instructions do not include boundary markers or specific warnings to the agent about ignoring potential instructions embedded in the captured text or clipboard data.
  • Capability inventory: The skill provides extensive capabilities to act upon the system, including fill (typing), click (interaction), and file-dialog (filesystem navigation) commands across SKILL.md.
  • Sanitization: No sanitization or validation steps are defined for the data ingested from the UI or clipboard before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 05:01 PM