rerun-urdf
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes links to official example code and reference materials hosted on the vendor's public GitHub repository.\n
- Evidence: References
github.com/rerun-io/rerun/tree/main/examples/python/robot_data_preprocessingandgithub.com/rerun-io/rerun/tree/main/examples/python/animated_urdffor implementation guidance.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external URDF files and telemetry data, which defines a standard data ingestion surface.\n - Ingestion points: Data is loaded via
UrdfTree.from_file_path(urdf_path)and ingested from external streams viasource_joint_state_stream()as described inSKILL.md.\n - Boundary markers: The skill relies on structured API calls and does not specify specialized delimiters to distinguish raw data from potential control instructions.\n
- Capability inventory: The execution environment includes
Read,Grep,Bash, andWebFetchtools to support data processing and logging workflows.\n - Sanitization: The examples include physical data validation, such as joint unit conversion and value clamping, but do not describe sanitization for natural language or control patterns embedded in the data sources.
Audit Metadata