{"items":[{"id":"NVI-00011900","kind":"vulnerability","title":"Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-x2rj-828p-hx9m","CVE-2026-61539"],"plain_summary":"GitHub lists this reviewed advisory for xinference. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-0ae2fb25a8ed3a37cba1325eb7d6b2e8"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-08T13:44:24.000Z","value":"10 critical","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-580f5f3b1994b5f0dfc54e070f951a2e"},{"kind":"EPSS","as_of":"2026-11-03T12:00:27.000Z","value":"1.226%","meaning":"FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.68863. Missing scores are unknown.","source_id":"sr-0ae2fb25a8ed3a37cba1325eb7d6b2e8"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-580f5f3b1994b5f0dfc54e070f951a2e","url":"https://github.com/advisories/GHSA-x2rj-828p-hx9m","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-x2rj-828p-hx9m","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:58:38.867Z"},{"id":"sr-0ae2fb25a8ed3a37cba1325eb7d6b2e8","url":"https://www.first.org/epss/data.html","basis":"official_catalog","notes":"FIRST EPSS; probability of exploitation in the next 30 days, not local compromise. Dataset date/model retained; FIRST services terms apply.","title":"CVE-2026-61539","publisher":"FIRST EPSS","observed_at":"2026-11-03T17:44:07.789Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-580f5f3b1994b5f0dfc54e070f951a2e"],"technology":"xinference","known_exclusions":[],"conditions_summary":"### Summary\n\nXinference used Python's unsafe `eval()` function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to return a Python expression. Xinference then evaluates that expression on the server while post-processing the tool-call result. In the tested default deployment, authentication was not enabled, so the vulnerability was exploitable by an unauthenticated remote attacker through the `/v1/chat/completions` endpoint.\n\n### Details\n\nUsers can interact with deployed models through Xinference's OpenAI-compatible `/v1/chat/completions` API. The request entry point is implemented in `xinference/api/restful_api.py`; non-streaming requests call the model instance's `chat()` method and return the inference result.\n\nWhen the Transformers backend is used, inference results flow through the batching logic in `xinference/model/llm/transformers/core.py`. Non-streaming chat results are handled by `handle_chat_result_non_streaming()`. If the request contains a `tools` field, Xinference calls `_post_proce","public_affected_ranges":["<= 2.5.0"]}],"null_published_at":"2026-11-04T10:04:41.581Z","source_updated_at":"2026-10-08T13:44:24.000Z","source_disclosed_at":"2026-08-21T20:56:37.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"Dated EPSS estimate updated; this is not a new disclosure or proof of exploitation.","null_first_observed_at":"2026-11-01T00:58:38.867Z"},{"id":"NVI-00011900","kind":"vulnerability","title":"Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-x2rj-828p-hx9m","CVE-2026-61539"],"plain_summary":"GitHub lists this reviewed advisory for xinference. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-580f5f3b1994b5f0dfc54e070f951a2e"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-08T13:44:24.000Z","value":"10 critical","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-580f5f3b1994b5f0dfc54e070f951a2e"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-580f5f3b1994b5f0dfc54e070f951a2e","url":"https://github.com/advisories/GHSA-x2rj-828p-hx9m","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-x2rj-828p-hx9m","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:58:38.867Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-580f5f3b1994b5f0dfc54e070f951a2e"],"technology":"xinference","known_exclusions":[],"conditions_summary":"### Summary\n\nXinference used Python's unsafe `eval()` function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to return a Python expression. Xinference then evaluates that expression on the server while post-processing the tool-call result. In the tested default deployment, authentication was not enabled, so the vulnerability was exploitable by an unauthenticated remote attacker through the `/v1/chat/completions` endpoint.\n\n### Details\n\nUsers can interact with deployed models through Xinference's OpenAI-compatible `/v1/chat/completions` API. The request entry point is implemented in `xinference/api/restful_api.py`; non-streaming requests call the model instance's `chat()` method and return the inference result.\n\nWhen the Transformers backend is used, inference results flow through the batching logic in `xinference/model/llm/transformers/core.py`. Non-streaming chat results are handled by `handle_chat_result_non_streaming()`. If the request contains a `tools` field, Xinference calls `_post_proce","public_affected_ranges":["<= 2.5.0"]}],"null_published_at":"2026-11-01T01:03:56.614Z","source_updated_at":"2026-10-08T13:44:24.000Z","source_disclosed_at":"2026-08-21T20:56:37.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-01T00:58:38.867Z"}],"next_cursor":null,"snapshot_revision":"42594"}