AgentReadyHomeAgent Listing

← irulescan MCP

irulescan MCP — agentic threat model

5.1AIVSS 5.1 · Medium

The irulescan MCP agent is a specialized static analysis tool with low autonomy, presenting a minimal risk profile focused primarily on the ingestion and processing of sensitive F5 BIG-IP configuration code.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 4.3AARS uplift 0.81Factor sum 1.5/10Threat ×0.95Mitigation ×1.0
Autonomy of Action
0.10
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.20
Persistent Memory
0.00
Contextual Awareness
0.30
Dynamic Identity
0.00
Multi-Agent Interactions
0.40
Non-Determinism
0.20
Opacity & Reflexivity
0.20

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 — The underlying foundation model is not specified, but the primary risk involves potential model evasion or adversarial inputs designed to bypass static analysis rules during TCL scanning.

L2 · Data Operations✓ mapped

The agent ingests sensitive network-appliance configuration code (F5 iRules). The primary data risk is the exposure or leakage of these proprietary configurations and network architectures during the analysis process.

L3 · Agent Frameworks✓ mapped

Exposed as an MCP tool, the framework risk is centered on how host agents invoke this tool. Maliciously crafted iRule payloads could attempt to exploit the parsing logic of the underlying irulescan tool.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The hosting environment of the MCP server is unspecified. If run locally or in an un-sandboxed container, a vulnerability in the parser could lead to local code execution or container escape.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of logging, evaluation, or guardrails to monitor the inputs received or the accuracy of the security findings returned to the calling agent.

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

Not certain from the listing — Access controls, authentication, and authorization mechanisms for the MCP endpoint are not detailed, which could allow unauthorized local or network entities to scan configurations.

L7 · Agent Ecosystem✓ mapped

Designed specifically for multi-agent or agent-to-tool ecosystems via MCP. The risk involves other agents blindly trusting the scan results or using the tool to validate malicious iRules before deployment.

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