CriticalVulnerabilityLLM-specific

CVE-2025-58357: 5ire content injection through chat page script gadgets

Source: NVD(opens in a new tab)
Identifier: CVE-2025-58357
Published: September 4, 2025
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.6%

Summary

CVE-2025-58357 affects 5ire, a cross-platform desktop AI assistant and model context protocol client, in version 0.13.2. The chat page's script gadgets enable content injection attacks through malicious prompt injection pages, compromised MCP servers, and exploited tool integrations. The source does not state the attacker's resulting impact.

Mitigation

Fixed in version 0.14.0.

Details

Scores and exploitation

CVSS score: 9.6(critical)
EPSS: 0.6%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-79
Attack pattern (CAPEC): CAPEC-198
CAPEC-86
AI threat technique (MITRE ATLAS): AML.T0051

Classification

Attack type: Prompt injection
Attack sophistication: Moderate
AI component targeted: Plugin
Impact: Integrity,
Confidentiality
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-58357

First tracked: February 15, 2026 at 08:52 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 93% (self-assessed)

Topics

Model Context Protocol

Summary

Mitigation

Topics

Related items