CVE-2025-50708
Published: 18 July 2025
Summary
CVE-2025-50708 is a high-severity Exposure of Sensitive Information to an Unauthorized Actor (CWE-200) vulnerability. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Credential Access (T1212); ranked in the top 45.6% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as APIs and Models; in the Privacy and Disclosure risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-21932
Vulnerability details
An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL
- CWE(s)
AI Security AnalysisAI
- AI Category
- APIs and Models
- Risk Domain
- Privacy and Disclosure
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, gpt-4, perplexity
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The vulnerability enables remote attackers to obtain sensitive information, likely including application access tokens, via the exposed token in shared chat URLs, facilitating exploitation for credential access and stealing application access tokens.
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Automated marking applies security attributes to system outputs, making it harder for attackers to exploit unmarked sensitive information leading to unauthorized exposure.
Proper attribute retention and permitted-value enforcement limits unauthorized actors from accessing sensitive information lacking correct labels.
Prevents unauthorized exposure of sensitive information by prohibiting untrusted external systems from processing or storing it.
By enforcing authorization matching prior to sharing, the control reduces the risk of exposing sensitive information to unauthorized actors.
Review and removal of nonpublic information from publicly accessible systems directly prevents exposure of sensitive data to unauthorized actors.
Data mining protection mechanisms detect and block unauthorized bulk extraction of sensitive data, directly mitigating exposure to unauthorized actors.
Literacy training teaches users to recognize and avoid actions that result in unauthorized exposure of sensitive information.
Retaining and monitoring training records confirms personnel have completed privacy and security awareness training on handling sensitive data, reducing the chance of unauthorized exposure due to lack of knowledge.