Network-Exposed Configuration Attacks on LLM-Controlled Social Robots
Organizations: University of Derby Derby, United Kingdom
Abstract
Large language models (LLMs) in embodied robots create security dependencies beyond inference. We investigate a network-exposed configuration attack on the Pollen Robotics Reachy Mini Lite, allowing an unauthenticated attacker to replace personality settings and the cloud LLM's system prompt through a management interface, without adversarial conversational input. Eleven prompt-injection attempts across five categories were reported as resisted, whereas both configuration-layer attack paths produced observable behavioural changes on physical hardware. We demonstrate local and network-adjacent access, mapping the weakness to CWE-306 (Missing Authentication for a Critical Function) and CWE-1327 (Binding to an Unrestricted IP Address), with a reported CVSS v3.1 score of 6.5 (Medium). A configuration endpoint also accepts cross-origin requests without a CORS preflight (CWE-352; 6.5 Medium), while the persistent-memory sink stores content without enforcing its stated restrictions. A source review of 59 public repositories identifies missing authentication in 10 of 11 source-verifiable genuine applications, or 11 of 11 including a framework-default case. These findings indicate recurrence within the sampled repositories, not prevalence in commercial products. We characterise a deployment gap between developer-oriented network assumptions and consumer-facing embodied AI security: inference-layer refusal cannot prevent unauthorised changes to model instructions. Potential consequences include surveillance through onboard cameras and microphones and social engineering of nearby users. Proof-of-concept code, evidence and the survey are available at https://bit.ly/reachypi.
Figures & tables
| Metric | Value | Rationale |
| Attack Vector | Adjacent (A) | Confirmed from a device on the same /24 subnet |
| Attack Complexity | Low (L) | Two HTTP POST requests; no prerequisites |
| Privileges Req. | None (N) | No authentication; confirmed by source code |
| User Interaction | None (N) | No operator action required |
| Scope | Unchanged (U) | Compromise within robot system boundary |
| Confidentiality | None (N) | Endpoints write configuration; no protected data read back |
| Vector | Source | Save | Apply | Observed |
|---|---|---|---|---|
| V1 Local | localhost | 200 | 200 | French response |
| V2 Remote | 192.168.0.25 | 200 | 200 | Spanish response |
| Endpoint | Status | Result |
|---|---|---|
| POST /personalities/save | 200 | Succeeded, no preflight |
| POST /personalities/apply | 422 | Rejected (requires JSON body) |
| Metric | Value | Rationale |
| Attack Vector | Network (N) | Malicious page may be hosted anywhere |
| Attack Complexity | Low (L) | Single auto-submitting form, confirmed on hardware |
| Privileges Req. | None (N) | No authentication required |
| User Interaction | Required (R) | Victim’s browser must load the page |
| Scope | Unchanged (U) | Same security authority as the main finding |
| Confidentiality | None (N) | save does not expose stored data |
| Surface | Att. | Succ. | Outcome |
|---|---|---|---|
| LLM inference | 11 | 0 | No manual injection succeeded |
| Local config. | 1 | 1 | Prompt modified |
| Network config. | 1 | 1 | Prompt modified |
| Memory sink | 4 | 4 | No content restriction enforced |
| Phase | Description |
|---|---|
| 1) Developer Intent | Prototyping tools bind to 0.0.0.0 so other machines on the developer’s own network can reach them during testing; a reasonable default for that context. |
| 2) Consumer Translation | The application ships into a consumer product without a security review: no authentication is added, the permissive bind is inherited unchanged. |
| 3) Cyber-Physical Consequence | Compromise now yields control over a physically present agent users trust, not the malfunction or data exposure typical of conventional IoT compromise. |
Cybersecurity
Cybersecurity develops methods to protect digital and cyber-physical systems from attacks, vulnerabilities, data loss, and misuse.
See all 379 papers