MediumVulnerabilityLLM-specific

CVE-2026-65698: Void path traversal in AI agent file-reading tools via injected instructions

Source: NVD(opens in a new tab)
Identifier: CVE-2026-65698
Published: July 23, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.5%

Summary

CVE-2026-65698 affects Void through 1.3.4, where the AI agent file-reading tools (read_file, ls_dir, get_dir_tree, and search_*) lack workspace confinement. A network-adjacent attacker who injects instructions into content the agent processes can supply absolute paths or file:// URIs to read arbitrary host files outside the open workspace. Because these tools bypass the approval gate, sensitive files such as SSH private keys or cloud credentials can be silently exfiltrated through subsequent tool calls.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 5.3(medium)
CVSS vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N
Attack vector: network
Attack complexity: high
Privileges required: none
User interaction: required
EPSS: 0.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 11, 2026.
Disclosure date: July 23, 2026

Weaknesses and techniques

Weakness (CWE): CWE-22
Attack pattern (CAPEC): CAPEC-126
AI threat technique (MITRE ATLAS): AML.T0051

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Moderate
AI component targeted: Agent
Impact: 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-2026-65698

First tracked: July 23, 2026 at 08:08 PM ET, from NVD/CVE Database

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

Classifier confidence: 90% (self-assessed)

Topics

AI agents

Summary

Mitigation

Topics

Related items