platynui
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables an agent to extract data from a desktop application's UI tree, which serves as a potential ingestion point for adversarial instructions embedded in element names or values. Ingestion points: The
Get AttributeandQuerykeywords (referenced inSKILL.mdandreferences/keywords-reference.md) allow the agent to read attributes such asName,Text, andValue. Boundary markers: There are no explicit instructions or delimiters defined to guide the agent in ignoring instructions found within the UI data. Capability inventory: The skill grants capabilities to perform actions based on interpreted data, includingKeyboard Type,Pointer Click, andActivate Window. Sanitization: No sanitization or validation logic is provided to filter UI content before it is processed by the agent. - [EXTERNAL_DOWNLOADS]: The skill requires the installation of dependencies from the Python Package Index (PyPI), a well-known package registry. Evidence: Instructions in
SKILL.mdandreferences/platform-setup.mdguide users to installrobotframework-PlatynUI,platynui-cli, andplatynui-inspectorusingpipanduvtools.
Audit Metadata