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.md and references/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 Apply changes 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
Risk Level
SAFE
Analyzed
Jun 23, 2026, 07:26 AM
Security Audit — agent-trust-hub — netbox-assurance