Newly released CVEs across every platform — sleek to read, verbose on demand, and served raw as markdown for AI and agent ingestion. Severity reads as depth: the deeper the contact, the graver the threat.
Depth = severity + exploitation
CVE-2026-115533NoneThe LeRobot library is vulnerable to arbitrary code execution via unsafe dynamic class instantiation in the from_pretrained() method and related paths. When loading a policy's processor configuration from a repository, the library uses …
CVE-2026-108857Low· 3.3Hugging Face Text Embeddings Inference through 1.9.4 contains a cleartext logging vulnerability that exposes the configured api_key because the router's Args struct lacks a redact attribute for it. Attackers with access to router logs, c…
CVE-2026-80047High· 7.8A vulnerability in Hugging Face Transformers (versions 4.57.0 to 5.16.1) allows remote Python files to be written to local disk without user consent when using GenerativePreTrainedModel.load_custom_generate(). The function fetches and ca…
CVE-2026-68770Critical· 9.8PoC⚖ disputedsentence-transformers contains a security control bypass vulnerability that allows attackers to achieve arbitrary code execution by exploiting a logic flaw in the import_module_class helper within sentence_transformers/util/misc.py, wher…
The beta is over. VulnSea now runs at vulnsea.com, every old beta link redirects to the same page, and your account, API keys and watchlists came with it. Plus a round of hardening, faster pages, and new request limits agents should know about.
A summary of everything that shipped over the last two weeks — the whole corpus is open, agents get change feeds, alias resolution and EPSS movers, and the data now includes CVE.org, vendor CSAF, aggregated exploits and per-source scores.
A step-by-step guide to plugging VulnSea into automated and agentic workflows — poll the delta, triage without burning tokens, match an SBOM, and let an MCP-native model do the reasoning.