AgentReadyHomeAgent Listing

← EasyCodeFinder

EasyCodeFinder — agentic threat model

7.0AIVSS 7.0 · High

EasyCodeFinder is a low-to-moderate risk open-source shopping agent. Its primary security exposure stems from real-time web scraping of untrusted sources (social media, coupon sites), making it highly susceptible to indirect prompt injection and serving malicious links to users.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 6.1AARS uplift 0.86Factor sum 2.2/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.30
Goal-Driven Planning
0.20
Self-Modification
0.00
Dynamic Tool Use
0.40
Persistent Memory
0.10
Contextual Awareness
0.40
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.50
Opacity & Reflexivity
0.30

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 uses a standard LLM for parsing search results and extracting coupon codes. Vulnerable to indirect prompt injection via poisoned web content or social media feeds.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — likely relies on real-time web scraping and search APIs rather than a persistent vector database. Vulnerable to data poisoning from malicious coupon sites hosting fake codes or malicious payloads.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — likely uses a lightweight orchestration framework to chain search queries and LLM parsing. Vulnerable to insecure tool integration if the web scraper executes untrusted JS or parses malicious payloads.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — being open-source, deployment is up to the host, but official hosted versions require secure sandboxing for web scraping activities to prevent SSRF or container escape.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no mention of guardrails or observability tools to detect when the agent extracts malicious URLs or hallucinated coupon codes.

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

Not certain from the listing — open-source nature allows code audits, but there are no mentioned compliance certifications (e.g., SOC2) or built-in access controls.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — operates as a standalone horizontal shopping agent with no indicated multi-agent or marketplace integrations.

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