SuperClaude — agentic threat model
SuperClaude presents a high agentic risk profile due to its integration of 23 subagents and 10 MCP tools directly into the local development environment via Claude Code, creating a massive attack surface for arbitrary code execution and tool misuse.
OWASP AIVSS score rationale
| Autonomy of Action | 0.80 | |
| Goal-Driven Planning | 0.80 | |
| Self-Modification | 0.50 | |
| Dynamic Tool Use | 0.90 | |
| Persistent Memory | 0.40 | |
| Contextual Awareness | 0.70 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.90 | |
| Non-Determinism | 0.70 | |
| Opacity & Reflexivity | 0.80 |
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.
Runs on top of Claude Code's foundation models. The primary threat is prompt injection or adversarial reprogramming of the large custom instruction set, which could hijack the 7 behavioral modes.
Not certain from the listing — the plugin operates on local codebases, but there is no explicit mention of a dedicated vector database, RAG pipeline, or data lineage controls.
Extremely high risk at the framework layer. Orchestrating 23 subagents, 29 slash commands, and 10 MCP tools creates a massive surface area for tool misuse, insecure tool integration, and unexpected agent-to-agent instruction loops.
Deploys locally within the user's terminal/development environment as a Claude Code plugin. The auto-configured AIRIS MCP Gateway introduces local network/process exposure, risking local host compromise if malicious commands are executed.
Not certain from the listing — there is no mention of built-in guardrails, evaluation frameworks, or logging/monitoring systems to detect drift or malicious subagent behavior.
Not certain from the listing — as an open-source plugin, it lacks explicit enterprise compliance, identity management, or authorization policies beyond Claude Code's native boundaries.
High risk of multi-agent trust abuse and cascading failures due to the interaction of 23 specialized subagents and external MCP servers without a defined isolation protocol.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).