CVE-2026-107183: Use After Free

llama.cpp before b11393 contains a use-after-free and double free vulnerability in commonchatpegmapper::map that allows unauthenticated remote attackers to corrupt heap memory via a dangling currenttool pointer. Attackers can submit a chatparser in a POST /completion request emitting a tool-id...

document-qa-engine (>=0.4.0, <=0.6.0), explainitall (>=1.0.0, <=1.0.2) +8 more potentially affected by CVE-2026-68770 via sentence-transformers (2.6.1)

sentence-transformers PYPI version 2.6.1 is affected by a known vulnerability. The following packages have a transitive dependency on sentence-transformers and may be impacted: - document-qa-engine =0.4.0, =1.0.0, =1.2.0, =0.0.14, =0.1.1, =0.1.3, =0.0.2, =0.0.3, =0.0.2, =0.1.5 Source cves:...

llama-index-collection (0.1.0), monocle-test-tools (>=0.6.6, <=0.8.10) +5 more potentially affected by CVE-2026-68770 via sentence-transformers (3.3.0)

sentence-transformers PYPI version 3.3.0 is affected by a known vulnerability. The following packages have a transitive dependency on sentence-transformers and may be impacted: - llama-index-collection 0.1.0 - monocle-test-tools =0.6.6, =1.1.3, =14.4.1, =0.1.1, =0.1.3 Source cves: CVE-2026-68770...

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to produce when the trigger appears. Existing evaluations typically fix the number of poisoned examples and sample them at random from a candidate...

Malicious code in intellectual-brown-llama (npm)

Source: amazon-inspector 7656a711e06044367e1796196dd8d15f923a002d41bacbfaa9b8ac6cbce98f47 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js, autopublish.js, autopublish2.js, autopublish3.js designed ...

Malicious code in ill-chocolate-llama (npm)

Source: amazon-inspector b5555ac2c54f83f5d6054d0c5ca3c988693b9e111b21e1e7d6e7350584dd3c05 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js, autopublish.js, autopublish2.js, autopublish3.js designed ...

Malicious code in embarrassed-yellow-llama (npm)

Source: amazon-inspector a2ff0fa496bf27bc99cfec9ea3aa1c8b49f3f56eccbdf553f56c7856ee5a7602 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js, autopublish.js, autopublish2.js, autopublish3.js designed ...

ag-llama-api (>=0.0.1, <=0.0.31), ag-llama-api-s (>=0.0.4, <=0.0.12) +23 more potentially affected by CVE-2026-69112 via accelerate (0.20.3)

accelerate PYPI version 0.20.3 is affected by a known vulnerability. The following packages have a transitive dependency on accelerate and may be impacted: - ag-llama-api =0.0.1, =0.0.4, =0.0.4, =0.0.11, =0.0.13, =0.0.15, =1.15.3, =1.16.3, =0.0.1, =2.0.0, =2.0.1.post2 - portfolio-agent 0.3.0rc1 a...

WordPress Quotes llama plugin < 3.1.6 - SQL Injection vulnerability

SQL Injection vulnerability discovered by Pablo González Pérez in WordPress Plugin Quotes llama versions 3.1.6...

CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding

Autoregressive language models can be used to transform a payload text into a stegotext of identical token length by preserving per-position rank information across contexts - a methodology we formalize as Contextual Autoregressive Rank Transcoding Steganography CARTS. While the Calgacus...

Malicious code in drunk-aquamarine-llama (npm)

Source: amazon-inspector 73a1f7004ce24ef63fc53b578b2dde94068b56c086d99403257e1eb93a09bcb4 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js, autopublish.js, autopublish2.js, autopublish3.js designed ...

CVE-2026-85673

LLaMA-Factory contains a server-side request forgery vulnerability in the OpenAI-compatible API multimodal media URL handler that allows unauthenticated attackers to bypass SSRF validation. The checkssrfurl guard validates URLs once but requests.get follows redirects and re-resolves DNS without...

CVE-2026-85666

OGX formerly Llama Stack, affected at commit fbe8e0f contains an unauthenticated server-side request forgery vulnerability in the OpenAI-compatible POST /v1/responses endpoint. MCP tool definitions accept a serverurl parameter along with headers and authorization values that is fetched server-sid...

CVE-2026-85673 LLaMA-Factory SSRF Guard Bypass via Redirect and DNS Rebinding

LLaMA-Factory contains a server-side request forgery vulnerability in the OpenAI-compatible API multimodal media URL handler that allows unauthenticated attackers to bypass SSRF validation. The checkssrfurl guard validates URLs once but requests.get follows redirects and re-resolves DNS without...

CVE-2026-85673 LLaMA-Factory SSRF Guard Bypass via Redirect and DNS Rebinding

LLaMA-Factory contains a server-side request forgery vulnerability in the OpenAI-compatible API multimodal media URL handler that allows unauthenticated attackers to bypass SSRF validation. The checkssrfurl guard validates URLs once but requests.get follows redirects and re-resolves DNS without...

CVE-2026-85673

LLaMA-Factory contains a server-side request forgery (SSRF) vulnerability in its OpenAI-compatible API multimodal media URL handler . The root cause is that the check_ssrf_url guard validates a URL only once, while requests.get subsequently follows HTTP redirects and re-resolves DNS without re-va...

EUVD-2026-71129

LLaMA-Factory contains a server-side request forgery vulnerability in the OpenAI-compatible API multimodal media URL handler that allows unauthenticated attackers to bypass SSRF validation. The checkssrfurl guard validates URLs once but requests.get follows redirects and re-resolves DNS without...

CVE-2026-85673 LLaMA-Factory SSRF Guard Bypass via Redirect and DNS Rebinding

LLaMA-Factory contains a server-side request forgery vulnerability in the OpenAI-compatible API multimodal media URL handler that allows unauthenticated attackers to bypass SSRF validation. The checkssrfurl guard validates URLs once but requests.get follows redirects and re-resolves DNS without...

CVE-2026-85673

LLaMA-Factory contains a server-side request forgery vulnerability in the OpenAI-compatible API multimodal media URL handler that allows unauthenticated attackers to bypass SSRF validation. The checkssrfurl guard validates URLs once but requests.get follows redirects and re-resolves DNS without...

Malicious code in combative-jade-llama (npm)

Source: amazon-inspector 90542b7105c192894ed2ae9dbb4b05cba2a5ed0eca933fa5540056a463ebaf4c This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js, autopublish.js, autopublish2.js, autopublish3.js designed ...