AgentReadyHomeAgent ListingPricing

← ServiceGraph

ServiceGraph — agentic threat model

5.7AIVSS 5.7 · Medium

ServiceGraph acts as a data aggregator and API utility rather than an autonomous agent, presenting low direct agentic risk but serving as a critical supply-chain dependency for downstream agents that consume its commercial directory data.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 5.3AARS uplift 0.36Factor sum 0.8/10Threat ×0.95Mitigation ×1.0
Autonomy of Action
0.10
Goal-Driven Planning
0.00
Self-Modification
0.00
Dynamic Tool Use
0.10
Persistent Memory
0.00
Contextual Awareness
0.20
Dynamic Identity
0.00
Multi-Agent Interactions
0.10
Non-Determinism
0.20
Opacity & Reflexivity
0.10

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 — ServiceGraph is a data integration API and does not explicitly state which foundation models it uses internally (if any) to curate, search, or enrich the directory data.

L2 · Data Operations✓ mapped

ServiceGraph consolidates multiple curated datasets (agencies, directories, newsletters). Key threats include data poisoning of these sources, lineage/provenance gaps in the aggregated commercial data, and unauthorized scraping or exfiltration of the enriched metrics.

L3 · Agent Frameworks⚠ not certain from listing

Not certain from the listing — ServiceGraph is a tool/API designed to be integrated into downstream agent frameworks, but its own internal orchestration, planning, or tool-calling framework is not described.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — The hosting, sandboxing, and infrastructure security of the ServiceGraph API endpoint are not detailed, though standard API vulnerabilities like credential exposure and denial of service apply.

L5 · Evaluation & Observability⚠ not certain from listing

Not certain from the listing — There is no mention of evaluation, monitoring, logging, or drift detection mechanisms for the data served by the API.

L6 · Security & Compliance (cross-cutting)✓ mapped

ServiceGraph uses a single API key for access control to multiple datasets. Threats include API key theft, lack of fine-grained authorization (AuthZ) for different datasets, and compliance risks regarding the commercial use of aggregated directory data.

L7 · Agent Ecosystem✓ mapped

ServiceGraph is designed to be dropped into other AI agents' stacks. This introduces supply chain risks where a compromise of ServiceGraph or its data integrity cascades to all downstream agents relying on its data for research, lead generation, or market analysis.

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

These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.