netbox-assurance
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill describes an architecture that ingests and processes data from external network devices, which can potentially contain malicious instructions intended to influence the agent during review.
- Ingestion points: Network data is ingested via Discovery agents or the Diode SDK as described in
SKILL.mdandreferences/data-sources.md. - Boundary markers: The instructions do not specify the use of delimiters or specific "ignore" markers to isolate the agent from instructions potentially hidden in ingested data fields like hostnames or interface descriptions.
- Capability inventory: The skill documents capabilities to
Applychanges to the NetBox source of truth and perform other state transitions using the NetBox Platform MCP. - Sanitization: There is no documentation regarding the validation or sanitization of ingested network data before it enters the agent's context for triage.
Audit Metadata