orionbelt-ontology-builder
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions in
SKILL.mdandreferences/upstream.mddescribe installing theorionbelt-ontology-builderpackage from a public registry using theuvtool. While the skill includes approval gates, this involves downloading and running code from an external source. - [COMMAND_EXECUTION]: The agent is instructed to use
Bashto install and launch the workbench application (orionbelt-ontology-builder). The instructions explicitly require the agent to seek user approval before executing these commands. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and edit user-supplied ontology data (OWL/SKOS), which could potentially contain malicious instructions or malformed data designed to influence agent behavior.
- Ingestion points: The agent uses the
Readtool to process user-provided ontology files and local source code repositories. - Boundary markers: The instructions mandate previewing diffs, identifying target ontologies, and obtaining authorization before writing data or applying imports.
- Capability inventory: The agent has access to shell execution via
Bashand file system access throughRead,Grep, andGlobtools. - Sanitization: The skill documentation suggests using review panels, change reports, and validation steps to manage the risks of importing external data.
Audit Metadata