sensor-fusion
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill identifies the 'openclaw' Python package and the 'api.openclaw.io' API endpoint as dependencies. These are standard resources for the OpenClaw IoT framework mentioned throughout the documentation.
- [COMMAND_EXECUTION]: The skill provides instructions for executing commands via the 'claw' CLI tool to perform sensor fusion and simulations. These commands are integral to the skill's primary functionality.
- [PROMPT_INJECTION]: The skill processes external data from sensors and configuration files, creating a potential surface for indirect prompt injection. * Ingestion points: Processes JSON data streams from sensors and configuration settings from 'config.json'. * Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands within the sensor data. * Capability inventory: The skill interacts with external APIs ('api.openclaw.io') and executes local CLI commands. * Sanitization: There is no evidence of data sanitization or validation of the sensor inputs before processing.
Audit Metadata