Capital Companion — agentic threat model
Capital Companion acts as an advisory financial agent with moderate risk; while it lacks direct trade execution capabilities, a compromise of its recommendation engine or data sources could lead to severe financial misinformation, market manipulation, or compliance violations.
OWASP AIVSS score rationale
| Autonomy of Action | 0.20 | |
| Goal-Driven Planning | 0.30 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.30 | |
| Persistent Memory | 0.40 | |
| Contextual Awareness | 0.70 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.60 | |
| Opacity & Reflexivity | 0.50 |
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 — likely relies on a proprietary or commercial LLM optimized for financial analysis. It is vulnerable to prompt injection attacks that could bypass safety guardrails to generate unauthorized financial advice or biased stock recommendations.
Not certain from the listing — ingests vast amounts of real-time financial data, news, and market sentiment. This creates a high exposure to data poisoning attacks, where malicious actors could manipulate news feeds or sentiment metrics to skew the agent's trading recommendations.
Not certain from the listing — orchestrates technical analysis tools and risk metrics based on user queries. Vulnerabilities could arise from insecure tool integration, allowing prompt injections to trigger unintended data queries or system commands.
Not certain from the listing — deployed as a closed-source, freemium SaaS application. Standard cloud infrastructure risks apply, including potential exposure of user session data or personalized investment profiles if the hosting environment is compromised.
Not certain from the listing — no details are provided regarding real-time monitoring, drift detection, or output guardrails. A lack of observability could allow silent failures or biased recommendations to persist undetected.
Not certain from the listing — financial advisory tools operate in a highly regulated space. The absence of explicit compliance certifications (e.g., SOC2) or clear disclaimers regarding automated financial advice poses significant regulatory and liability risks.
Not certain from the listing — operates primarily as a standalone assistant. There is no evidence of multi-agent collaboration or marketplace integrations, minimizing ecosystem-specific cascading risks.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).