pyside6-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external project files, including PySide6 source code, architecture documentation, and .ui files. This creates a surface where malicious instructions embedded in these files could attempt to influence agent behavior.
- Ingestion points: Instructions in
SKILL.mdandreferences/project_workflow.mdrequire the agent to inspect existing application source code, UI definitions, and existing documentation to identify architecture and design patterns. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers to differentiate between instructions and the data being analyzed.
- Capability inventory: The skill has capabilities for file system access and shell command execution for development tools like
pyside6-uicand testing tools likepytest-qtandscreencapture. - Sanitization: There is no mention of sanitizing or validating the content of ingested code or documentation before processing.
- [COMMAND_EXECUTION]: The skill utilizes several command-line tools as part of the standard PySide6 development and testing lifecycle.
- Evidence:
references/official_qt_for_python_docs.mdandreferences/designer_ui_workflow.mdreference the use ofpyside6-uic,pyside6-rcc, andpyside6-project.references/testing_and_oracles.mdsuggests using thescreencapturesystem utility (on macOS) andpytest-qtto generate visual and functional proof artifacts.
Audit Metadata