Security readout for executives and security teams
Plain-English summary
Langroid applications using Neo4jChatAgent before 0.65.5 may let attacker-influenced prompts become database queries. That can expose or destroy graph data. In higher-risk Neo4j configurations with APOC or dbms.security procedures enabled, the advisory says filesystem or OS-command access may be possible.
Executive priority
Treat this as urgent for any Langroid system connected to Neo4j. Prioritize externally reachable chat, agent, or RAG applications because normal user input may be enough to influence database operations.
Technical view
Neo4jChatAgent executed LLM-generated Cypher through the Neo4j driver without validation, a statement-type allowlist, or an opt-out gate. Prompt injection through user input or retrieved content could influence Cypher execution. The issue affects langroid versions before 0.65.5 and is fixed in 0.65.5.
Likely exposure
Exposure is likely limited to Langroid deployments using Neo4jChatAgent with attacker-influenceable prompts or RAG content. Impact increases when the Neo4j account is highly privileged or server-side APOC/dbms.security procedures are enabled.
Exploitation context
No provided source reports active exploitation, and KEV is false. The threat model is prompt-to-Cypher injection: attacker-controlled or indirect prompt content changes generated Cypher that the agent executes without validation.
Researcher notes
The public bundle attributes the flaw to missing Cypher validation in Neo4jChatAgent and compares it to the earlier SQLChatAgent issue. Sources identify the affected range and fixed version, but do not provide independent exploitation evidence.
Mitigation direction
- Upgrade langroid to version 0.65.5 or later.
- Pause or restrict Neo4jChatAgent use until upgraded.
- Run Neo4j with least-privilege credentials for Langroid integrations.
- Disable or tightly restrict risky Neo4j APOC and dbms.security procedures.
- Check vendor guidance before applying compensating controls not documented in sources.
Validation and detection
- Inventory applications and lockfiles for langroid versions below 0.65.5.
- Identify code paths using Neo4jChatAgent or Neo4j-backed RAG workflows.
- Verify deployed environments actually run the upgraded dependency.
- Review Neo4j privileges granted to the Langroid application account.
- Inspect Neo4j logs for unexpected writes, deletes, or procedure calls.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-74: Exact CWE lookup
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-55615 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Critical
- CVSS
- 9.2 (4.0)
- Known Exploited
- No
- Published
Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N——GitHub_MVulnerability scoring details
Base CVSS 4.0 score
9.2CriticalVector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/langroid/langroid/security/advisories/GHSA-2pq5-3q89-j7ccCVE reference, GitHub_M · x_refsource_CONFIRM
- https://github.com/langroid/langroid/commit/5a3097d9dd6378b08ced5480b0caf76cc58d00faCVE reference, GitHub_M · x_refsource_MISC
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.