Vllm-orchestrator-gateway: vllm-orchestrator-gateway: authorization header and full chat payloads logged at hard-coded debug default
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
- Exploitation: none
- Automatable: yes
- Technical impact: partial
Summary
The vllm-orchestrator-gateway component, which routes requests for vLLM-based AI deployments, is affected. Its production build writes incoming authorization headers (including bearer tokens) and full chat message contents to persistent logs, so anyone with access to those logs can read credentials and private conversation data.
Summarized by anthropic/claude-haiku-5.5. Verify details against the original sources.
Read the original description
A flaw was found in the vllm-orchestrator-gateway component. The system's production binary logs all incoming authorization headers and full chat payloads, which may contain personally identifiable information (PII) and secrets, to persistent logs. This sensitive data, including bearer tokens and chat content, can be accessed by any user with logging privileges. This vulnerability leads to information disclosure, potentially allowing an attacker to harvest credentials and sensitive conversation content.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: none · Automatable: yes · Technical impact: partial
- Record last updated
Affected versions
- rhoai/odh-trustyai-vllm-orchestrator-gateway-rhel9
Version range not reported
- rhoai/odh-trustyai-vllm-orchestrator-gateway-rhel9
Version range not reported