AgentReadyHomeAgent Listing

← Acedit

Acedit — agentic threat model

5.7AIVSS 5.7 · Medium

Acedit is a low-risk, vertical AI coaching agent primarily handling text-based mock interviews and resume analysis. Its main security exposures lie in the handling of user PII (resumes) and the potential for prompt injection, with minimal risk of autonomous real-world harm.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 4.8AARS uplift 1.2Factor sum 2.3/10Threat ×1.0Mitigation ×0.95
Autonomy of Action
0.20
Goal-Driven Planning
0.30
Self-Modification
0.00
Dynamic Tool Use
0.10
Persistent Memory
0.30
Contextual Awareness
0.40
Dynamic Identity
0.00
Multi-Agent Interactions
0.00
Non-Determinism
0.60
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.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — likely relies on commercial or open-source LLMs (e.g., GPT-4, Llama) for generating interview questions and feedback. Risks include prompt injection to bypass coaching guardrails or generate inappropriate content.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — likely processes user-uploaded resumes and job descriptions to tailor mock interviews. Risks include data exfiltration of sensitive PII contained in resumes, or poisoning of the mock interview context.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — likely uses a standard orchestration framework (e.g., LangChain) to manage the mock interview flow. Risks include insecure state management or session hijacking during real-time support.

L4 · Deployment & Infrastructure✓ mapped

As an open-source tool, deployment depends on the user's hosting choice or a central hosted version. Risks include insecure default configurations in self-hosted environments or exposed API keys.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no explicit mention of evaluation or observability guardrails. Risks include lack of monitoring for toxic or biased feedback generated during mock interviews.

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

Not certain from the listing — compliance posture (e.g., GDPR for resume data) is unspecified. Risks include non-compliance with data privacy regulations if user resumes are stored without proper consent or encryption.

L7 · Agent Ecosystem✓ mapped

The agent operates as a standalone vertical application with no indicated multi-agent or marketplace integrations, minimizing ecosystem-level cascading risks.

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