slug: patronus-protect
provider: Patronus Protect
generated_by: planning/capability-mapping/scripts/classify_capabilities.py
model: claude-opus-5
frame:
- Software & Technology
min_confidence: 0.7
capability_model:
  source: https://github.com/vincentmakes/turbo-ea-capabilities
  license: CC-BY-4.0
  attribution: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities,
    CC BY 4.0
  notice: NOTICE
edge_count: 1
edges:
- tag: Scan
  spec_file: patronus-protect-scan-api-openapi.yml
  capability_id: BC-620
  capability_id_l1: BC-620
  capability_name: Cybersecurity Management
  confidence: 0.8
  evidence: '"on-device AI firewall that detects prompt injection, PII/DLP, sensitive documents and agentic
    tool risk"; schemas "SafetyStatus", "TextScan", "UrlScan", "McpServerScan", "DecisionEvidence"'
  reason: The scan operations submit text, URLs, documents and MCP servers and return safety verdicts
    for injection and sensitive-data risk — a security screening control. Clearly Cybersecurity Management
    at L1; the sub-capability is ambiguous between threat detection, vulnerability scanning and privacy/data-protection
    filtering, so no L2 asserted.