AgentReadyHomeAgent Listing

← solo-dev

solo-dev — agentic threat model

9.3AIVSS 9.3 · Critical

The solo-dev agent presents a high-risk profile due to its ability to autonomously read and modify the local working tree and execute development workflows, meaning a compromise could lead to direct arbitrary code execution or supply chain injection.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.2AARS uplift 1.06Factor sum 5.6/10Threat ×1.05Mitigation ×1.0
Autonomy of Action
0.80
Goal-Driven Planning
0.80
Self-Modification
0.30
Dynamic Tool Use
0.70
Persistent Memory
0.40
Contextual Awareness
0.60
Dynamic Identity
0.20
Multi-Agent Interactions
0.50
Non-Determinism
0.70
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — relies on Claude Code (Anthropic Claude models) as its foundation. Threats include prompt injection bypassing system instructions to execute malicious commands on the local working tree.

L2 · Data Operations✓ mapped

Operates directly on the local working tree. Risks include unauthorized reading of sensitive local files, source code exfiltration, or poisoning of the codebase via malicious inputs.

L3 · Agent Frameworks✓ mapped

Uses planning, implementing, and reviewing agents to automate the dev loop. Vulnerable to tool misuse where the agent is manipulated into executing destructive file modifications or shell commands.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — runs locally as a Claude Code plugin. If executed without containerization or sandboxing, a compromise allows direct host-level privilege escalation and lateral movement.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no built-in logging, guardrails, or anomaly detection are mentioned. Blind spots in monitoring could allow malicious code modifications to go unnoticed.

L6 · Security & Compliance (cross-cutting)⚠ not certain from listing

Not certain from the listing — lacks explicit mention of access controls, audit logging, or policy enforcement. Relies entirely on the user's local environment security.

L7 · Agent Ecosystem✓ mapped

Bundles multiple sub-agents (planning, implementing, reviewing). Risks include cascading failures or trust abuse where a compromised planning agent misleads the implementing agent.

MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).