interface-edit
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local validation script (interface-validate.py or interface-validate.ps1) after editing the XML file to ensure structural integrity. These calls use relative paths within the skill's directory structure and target known validator scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied JSON data and reads existing XML configuration files. While this represents a theoretical attack surface for indirect prompt injection, the skill uses standard JSON and XML parsers and only modifies specific configuration elements, which is consistent with its stated purpose of managing command visibility and placement.
Audit Metadata