Protocraft AI — agentic threat model
Protocraft AI presents a high agentic risk due to its local execution model with direct read/write access to the host filesystem and code editing capabilities, combined with a lack of sandboxing or explicit security guardrails.
OWASP AIVSS score rationale
| Autonomy of Action | 0.70 | |
| Goal-Driven Planning | 0.80 | |
| Self-Modification | 0.50 | |
| Dynamic Tool Use | 0.80 | |
| Persistent Memory | 0.50 | |
| Contextual Awareness | 0.80 | |
| Dynamic Identity | 0.20 | |
| Multi-Agent Interactions | 0.70 | |
| Non-Determinism | 0.80 | |
| 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 — Protocraft supports external APIs (OpenAI, Anthropic, OpenRouter) and local LLMs. It is vulnerable to model-specific threats like prompt injection, adversarial inputs, or misaligned outputs depending on the chosen backend.
Protocraft operates directly on local files, spreadsheets, and PDFs. The primary threat is data exfiltration or local file corruption/poisoning if malicious files are processed via prompt injection.
The agent supports complex workflows, file/code editing, and tool use. Insecure tool integration or prompt injection could lead to unauthorized local file modification or execution of malicious code.
Runs locally on Windows, Mac, and Linux. There is no mention of sandboxing or containerization, meaning compromised agent workflows could execute with the privileges of the local user.
Not certain from the listing — No built-in logging, guardrails, or evaluation frameworks are detailed for monitoring agent decisions or detecting anomalous file operations.
Not certain from the listing — As a closed-source desktop application, there is no mention of enterprise compliance standards, access controls, or audit logging for file modifications.
Allows users to 'create agents for complex workflows'. This introduces risks of cascading failures or multi-agent trust abuse if downstream agents execute actions without strict boundaries.
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.