CVE-2026-59822
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced …
Read full description
Attention and evidence
Evidence confidence: Exploitation recorded
Hype components
Sources and documents
Score evolution
● Hype ● Reality
Earlier evidence-support scores are retained in history; this chart shows only the current priority definition.
First record: hype 1.8 · reality 8.3 (2026-11-02 15:14). The curve appears once the score changes.
Public exploit evidence
Public exploit entries / repo candidates
Evidence context and dated references
Reality is general threat/review priority, combining observed exploitation, CVSS severity and fresh EPSS. Evidence confidence is separate. This is not calibrated risk, a victim count or an asset-specific assessment. A range reflects missing numeric inputs.
Evidence in context
- Confidence in exploitation evidence
- Exploitation recorded
- Priority basis
- Recorded exploitation; CVSS 8.8; EPSS 0.8%
- Attention, last 30 days
- 1 distinct story titles; 1 press documents; 1 publisher domains.
- Technical potential
- network access, no prior privileges, no user interaction.
- Observed activity
- Exploitation recorded in CISA KEV.
- Known scale
- Not quantified.
- Evidence confidence basis
- Trusted exploitation confirmation
Score evaluated: 2026-11-05 14:00:17.665024+00:00 · EPSS snapshot: 2026-11-05T12:03:04Z