Wispy — agentic threat model
Wispy presents a moderate risk profile primarily driven by indirect prompt injection via the web pages it browses, which could lead to data exfiltration or generation of malicious content. The lack of explicit sandboxing or security controls in the listing increases its vulnerability to web-based exploits.
OWASP AIVSS score rationale
| Autonomy of Action | 0.40 | |
| Goal-Driven Planning | 0.30 | |
| Self-Modification | 0.00 | |
| Dynamic Tool Use | 0.30 | |
| Persistent Memory | 0.10 | |
| Contextual Awareness | 0.50 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.00 | |
| Non-Determinism | 0.60 | |
| Opacity & Reflexivity | 0.40 |
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 — Wispy likely relies on a commercial or open-source LLM for summarization and generation. It is vulnerable to prompt injection via web content (indirect prompt injection) and model misalignment.
Not certain from the listing — Wispy processes real-time web data. It faces risks of data poisoning from malicious web pages and potential exfiltration of sensitive browsed content.
Not certain from the listing — The orchestration framework manages browser tool execution. Risks include insecure tool integration where malicious web inputs hijack the browser controller.
Not certain from the listing — It is unclear if the browser runs in a secure, isolated sandbox or directly on the user's local machine, posing local execution or SSRF risks.
Not certain from the listing — No built-in guardrails or logging mechanisms are described to detect prompt injection or malicious web content processing.
Not certain from the listing — There is no mention of authentication, data privacy compliance (e.g., GDPR), or access controls over what URLs the agent can browse.
Not certain from the listing — Wispy operates as a standalone browser assistant with no indicated multi-agent or marketplace integrations.
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.