AgentReadyHomeAgent Listing

← English Compiler

English Compiler — agentic threat model

7.0AIVSS 7.0 · High

The English Compiler is a low-autonomy proof-of-concept utility for code generation, presenting primary risks around prompt injection leading to malicious code generation (supply chain risk) and a lack of execution sandboxing.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 6.3AARS uplift 0.7Factor sum 1.9/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.20
Goal-Driven Planning
0.30
Self-Modification
0.00
Dynamic Tool Use
0.10
Persistent Memory
0.00
Contextual Awareness
0.20
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely relies on a commercial or open-source LLM (e.g., GPT-4, Llama) for code generation. Vulnerable to prompt injection where malicious markdown specs lead to the generation of backdoored or vulnerable code.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — as an open-source POC, it likely does not use a complex vector database or RAG, but rather direct prompt context. If RAG is used, data poisoning of reference templates is a threat.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — likely uses a simple script or basic LLM orchestration framework to parse markdown and call the LLM. Risk of insecure tool integration if it attempts to automatically run or test the generated code.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — being an open-source POC, deployment is likely local or self-hosted. If hosted, lack of sandboxing during code generation or execution could lead to remote code execution (RCE) on the host.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — likely lacks robust guardrails, output validation, or logging, making it difficult to detect when the compiler generates malicious or highly vulnerable code.

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

Not certain from the listing — as a POC, it likely lacks authentication, authorization, or compliance controls, presenting significant supply chain risks if integrated into a CI/CD pipeline without manual review.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — does not appear to interact with an agent ecosystem or marketplace, operating as a standalone utility.

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