Shortcut (Excel AI) — agentic threat model
Shortcut presents a moderate-to-high risk profile due to its access to highly sensitive corporate financial data and its integration as a native Excel add-in, which could be leveraged for formula injection or data exfiltration.
OWASP AIVSS score rationale
| Autonomy of Action | 0.40 | |
| Goal-Driven Planning | 0.60 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.40 | |
| Persistent Memory | 0.20 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.10 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.50 | |
| Opacity & Reflexivity | 0.40 |
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 commercial LLMs for formula generation and financial modeling. Threats include adversarial prompt injection to manipulate financial outputs or generate malicious Excel formulas.
Not certain from the listing — processes user-uploaded spreadsheets and financial data. Threats include data exfiltration of sensitive proprietary financial models and lack of clear data retention/privacy policies.
Not certain from the listing — orchestrates multi-turn edits and formula generation. Threats include insecure tool integration (Excel API manipulation) and formula injection (e.g., generating malicious Excel formulas like WEBSERVICE to exfiltrate data).
Not certain from the listing — hosted as a web app and native Excel add-in. Threats include insecure communication between the Excel add-in and the backend, and lack of sandboxing for formula execution.
Not certain from the listing — mentions 'audits' but likely refers to spreadsheet auditing rather than LLM observability. Threats include lack of guardrails against generating incorrect or malicious financial formulas.
Not certain from the listing — no explicit security certifications (like SOC2) or compliance frameworks mentioned. Threats include unauthorized access to sensitive corporate financial data.
Not certain from the listing — operates primarily as a standalone Excel add-in/web app. Threats include potential supply chain risks via the Excel Add-in store.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.