LightLLM through 1.2.0 Missing Authentication on RL Control Routes
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| ModelTC | LightLLM | unaffected |
|
No data.
No data.
| Vendor | Product | Versions | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Modeltc | Lightllm |
|
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.513% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Modeltc
Modeltc lightllm |
|
| Vendors & Products |
Modeltc
Modeltc lightllm |
| Type | Values Removed | Values Added |
|---|---|---|
| Description | LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call endpoints like /pause_generation, /abort_request, /flush_cache, and /init_weights_update_group to disrupt inference operations and wedge workers on deployments started with --enable_rl. | |
| Title | LightLLM through 1.2.0 Missing Authentication on RL Control Routes | |
| Weaknesses | CWE-306 | |
| References |
|
|
| Metrics |
cvssV3_1
|