Biliki AI — agentic threat model
Biliki AI is a low-to-moderate risk travel assistant focused on eco-friendly recommendations. Its primary security risks stem from its reliance on third-party affiliation APIs and the potential for prompt injection to manipulate travel recommendations or redirect users to malicious booking sites.
OWASP AIVSS score rationale
| Autonomy of Action | 0.20 | |
| Goal-Driven Planning | 0.30 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.30 | |
| Persistent Memory | 0.10 | |
| Contextual Awareness | 0.40 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.50 | |
| Opacity & Reflexivity | 0.30 |
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.
Not certain from the listing — Biliki AI likely relies on third-party LLMs to process user interests and generate itineraries. Vulnerable to prompt injection that could bypass sustainability filters or generate inappropriate content.
Not certain from the listing — Requires a database of eco-friendly accommodations, experiences, and CO2 emission factors. Vulnerable to data poisoning of sustainability metrics or database exfiltration.
Not certain from the listing — Uses pre-set prompts to orchestrate itinerary generation. Vulnerable to prompt injection that could hijack the logic flow or manipulate the CO2 calculator inputs.
Not certain from the listing — Exposed as a web platform and API. Vulnerable to standard web/API vulnerabilities, including unauthorized API access or denial of service.
Not certain from the listing — No explicit mention of real-time monitoring or guardrails. Vulnerable to outputting hallucinated, closed, or unsafe travel recommendations without detection.
Not certain from the listing — Collects user travel dates, destinations, and interests. Lack of visible compliance frameworks (like GDPR) poses a risk of unauthorized PII exposure.
Biliki AI relies on 'Strategic Affiliation Partnerships' to offer accommodations and experiences. This ecosystem exposure introduces risks of third-party API compromise, leading to malicious redirects or fraudulent booking links.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).