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-2026-53870Medium· 5.5Hermes Agent creates response_store.db and webhook_subscriptions.json with world-readable permissions (mode 0o644)
CVE-2026-53869High· 7.5Hermes Agent contains a DNS rebinding vulnerability in WebSocket endpoints that allows remote attackers to bypass Host and Origin validation
CVE-2026-10224Medium· 5.3hermes-agent has an Uncontrolled Resource Consumption issue
CVE-2026-10223Medium· 6.3hermes-agent has an Injection issue
CVE-2026-10221High· 7.3hermes-agent has an Injection issue
CVE-2026-10222Medium· 5.6hermes-agent has an Injection issue
CVE-2026-9368High· 7.3hermes-agent has a sandbox issue
CVE-2026-9366High· 7.3hermes-agent has an Injection issue
CVE-2026-9369Medium· 5.3hermes-agent has an Incorrect Comparison
CVE-2026-9353High· 7.3hermes-agent has an Injection issue
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.
CVE and 0day intelligence that reads like an instrument — built for analysts and AI agents alike. Here's what it does and where it's going.