Secure Autonomous
FeedbackGet alertsCheck a deployment
Signals › SIG-2026-11-06-001

CVE-2026-87008: Code Graph RAG's structural search and replace tools can follow a symbolic link planted in an analyzed repository to read or overwrite files outside the project root (fixed in 0.0.589)

The National Vulnerability Database (NVD) record says that before 0.0.589 Code Graph RAG checked containment on unresolved paths, so a symbolic link in an analyzed repository lets the structural_search tool disclose files outside the configured root without an approval gate and lets structural_replace with dry_run=False overwrite writable ones, and the Model Context Protocol (MCP) path invokes structural replacement without the agent-loop approval control.

VulnerabilitySoftware agents · Enterprise work agentsRecord published 2026-11-05Posted 2026-11-06
SIG-2026-11-06-001National Vulnerability Database record ↗

The record

Kind
Vulnerability
Source record
CVE-2026-87008: Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing (National Vulnerability Database record)
Record published
2026-11-05
Posted here
2026-11-06
World
Software agents · Enterprise work agents
Controls concerned
Containment and isolation C-E5; Destructive-action gate C-E3
Checked
Checked against its record on 2026-11-06 by a reader who did not draft it; report verification/reports/SIG-2026-11-06-001-2026-11-06.md.

A signal's controls are the ones its record points at, the exposure; a case's controls are the ones its records show were absent or failed, so the two can differ.

Corrections

Changes to what this signal says, with the reason. Every earlier version is kept.

What a signal is. A signal records what a primary record says; it assigns no fault. It is lighter than a case: one dated item from one record, tagged with the world, sector and controls it touches. It becomes a case when it meets the bar for one.

New signals like this, once a week. A short email when a case, signal or rule touches software agents. Free; unsubscribe in one click.

Get the weekly email

Newer: CVE-2026-113663: AG2's sandbox shell tool filter misses newline separators, so an attacker-influenced agent command can run an extra arbitrary statement, which runs on the host under the default backend (fixed in ag2 1.1.1)
Older: Acronis Threat Research Unit report: a single operator used BOSSAI, a mesh of 12 artificial intelligence (AI) agents, to target hundreds of organizations in eleven countries, with confirmed breaches at universities and emergency services providers (November 2026)

Is this wrong? Dispute it with the record that shows otherwise. All signals · RSS feed.

Help shape the Register

A person reads every answer; changes it leads to are logged in the methodology. To dispute a claim or reply for a named company, use Respond, dispute, or submit.

Did this page help with what you came to do?