Lecca.io — agentic threat model
Lecca.io presents a high-risk profile due to its integration of AI agents with web and phone tools and multi-agent workflow execution, though this is partially mitigated by its SOC 2 Type II compliance.
OWASP AIVSS score rationale
| Autonomy of Action | 0.80 | |
| Goal-Driven Planning | 0.70 | |
| Self-Modification | 0.20 | |
| Dynamic Tool Use | 0.80 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.70 | |
| Dynamic Identity | 0.40 | |
| Multi-Agent Interactions | 0.80 | |
| Non-Determinism | 0.60 | |
| Opacity & Reflexivity | 0.60 |
Scored with the canonical OWASP AIVSS formula (AIVSS calculator reference); agentic risk factors estimated from the agent’s described capabilities.
MAESTRO 7-layer threat model
Per-layer threats for this agent. Layers tagged “not certain from listing” are general, caveated commentary where the public description didn’t pin that layer.
Not certain from the listing — The specific foundation models used are not disclosed. Threats include model reprogramming or prompt injection that could hijack the downstream web and phone automation tools.
Not certain from the listing — The data ingestion, storage, and RAG mechanisms are not specified. Threats include data exfiltration of sensitive workflow variables or context through web/phone channels.
The platform orchestrates complex agent-to-workflow loops. Threats include insecure tool integration (especially phone/web dialers/scrapers) and unauthorized tool execution via indirect prompt injection.
Not certain from the listing — The hosting infrastructure and sandboxing of web/phone execution environments are not described. Threats include infrastructure compromise or lateral movement via web-browsing agents.
Not certain from the listing — No built-in evaluation, guardrail, or observability features are detailed. Threats include blind spots in monitoring recursive agent-workflow loops.
The platform is SOC 2 Type II compliant, indicating verified organizational security controls, though specific runtime authorization policies for agent actions remain undefined in the listing.
High exposure due to native agent-to-agent and agent-to-workflow communication ('they can talk to each other'). Threats include cascading failures, infinite execution loops, and trust abuse between compromised agents.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).