The Agent Skills Directory

[SAFE]: The skill uses a vendor-specific CLI tool (uip) to perform UI automation tasks such as clicking, typing, and extracting data. This is consistent with its stated purpose.
[SAFE]: The skill references local documentation and prerequisites within the project directory, posing no external security risk.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it extracts data from running applications (e.g., table data, UI state). However, this is a standard requirement for UI automation and no malicious instructions or bypass attempts were detected in the skill's own code.
Ingestion points: Reading values and extracting data from live desktop/browser applications via uip rpa uia.
Boundary markers: None explicitly defined in the provided file.
Capability inventory: Executes uip CLI commands, reads files, and uses grep.
Sanitization: No specific sanitization or filtering logic is mentioned for the data extracted from UIs.

uipath-interact