AgentReadyHomeAgent Listing

← Qodo Skills

Qodo Skills — agentic threat model

8.6AIVSS 8.6 · High

Qodo Skills presents a moderate-to-high risk profile due to its direct integration into software development workflows and codebases. While it enhances code quality, a compromise could lead to source code exfiltration or the injection of malicious code during automated test generation.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 7.5AARS uplift 1.05Factor sum 4.2/10Threat ×1.0Mitigation ×1.0
Autonomy of Action
0.40
Goal-Driven Planning
0.50
Self-Modification
0.10
Dynamic Tool Use
0.60
Persistent Memory
0.20
Contextual Awareness
0.70
Dynamic Identity
0.20
Multi-Agent Interactions
0.40
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✓ mapped

Extends Claude as its foundation model. Primary threats include prompt injection to bypass security scanning rules or tricking the model into generating insecure code or tests.

L2 · Data Operations✓ mapped

Requires access to proprietary codebases to perform quality checks and test generation. Threats include unauthorized data exfiltration of source code or poisoning of the codebase context.

L3 · Agent Frameworks✓ mapped

Uses a composable skill library to orchestrate tasks. Threats include insecure tool integration where malicious code could be executed during test generation or scanning processes.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — No details are provided regarding where these skills are executed (e.g., local developer environment, CI/CD pipelines, or cloud sandboxes), raising potential container escape or host compromise risks if execution is unsandboxed.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of logging, guardrails, or observability mechanisms to monitor the skills' actions or detect anomalous code generation behavior.

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

Not certain from the listing — The directory listing does not specify access control policies, repository authentication mechanisms, or compliance certifications (like SOC2) for handling proprietary code.

L7 · Agent Ecosystem✓ mapped

Operates as a curated library of reusable capabilities extending Claude. Threats include the introduction of malicious or compromised skills into the library, leading to supply chain vulnerabilities.

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