AgentReadyHomeAgent Listing

← offensive-sqli (Claude-Red)

offensive-sqli (Claude-Red) — agentic threat model

9.4AIVSS 9.4 · Critical

The offensive-sqli agent presents a high-risk profile due to its capability to automate powerful exploitation tools like SQLmap and craft complex database injection payloads, lacking inherent safety controls in its open-source description.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.8AARS uplift 0.61Factor sum 4.6/10Threat ×1.1Mitigation ×1.0
Autonomy of Action
0.70
Goal-Driven Planning
0.80
Self-Modification
0.10
Dynamic Tool Use
0.80
Persistent Memory
0.20
Contextual Awareness
0.70
Dynamic Identity
0.10
Multi-Agent Interactions
0.10
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 utilizes a foundation model from the Claude family. Threats include prompt injection to bypass safety guardrails, allowing unauthorized generation of highly destructive exploit payloads.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — relies on knowledge of SQLi variants, ORM CVEs, and database structures. Threats include outdated vulnerability data or poisoning of local reference materials if RAG is used.

L3 · Agent Frameworks✓ mapped

The agent orchestrates SQLmap automation and payload crafting. Threats include insecure tool integration, where malicious target responses or inputs could lead to command injection within the agent's execution environment.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — deployment is user-managed. Threats include running the agent and SQLmap without proper sandboxing, potentially exposing the host system to compromise if a target database server counter-attacks.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — no monitoring or logging features are described. Threats include a lack of auditability, making it difficult to track or block unauthorized scanning and exploitation attempts.

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

Not certain from the listing — no built-in authorization or policy enforcement is mentioned. Threats include compliance violations and legal risks if the tool is used against targets without explicit authorization.

L7 · Agent Ecosystem⚠ not certain from listing

Not certain from the listing — no multi-agent interactions are specified. Threats include the agent being chained into larger, unmonitored offensive workflows that could cause cascading network or database failures.

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