claroty-ot-topology
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes potentially untrusted data from the Claroty xDome API, which could be used as a vector for indirect prompt injection.
- Ingestion points: Data from tools such as
get_device_communication_map,list_organization_zones, andlist_ot_activity_eventsis loaded into the agent's context. - Boundary markers: The skill definition does not specify delimiters or instructions for the agent to treat API responses as untrusted content.
- Capability inventory: The skill can execute local scripts via its MCP server (
claroty_mcp_server.py) and composes with visualization skills (canvas-network-viz,drawio-) that provide rendering and file-handling capabilities. - Sanitization: There is no evidence of sanitization, filtering, or schema validation mentioned in the skill instructions to mitigate the risk of instructions embedded in the API data being obeyed by the agent.
Audit Metadata