GHSA-898v-775g-777c is a critical-severity (CVSS 9.4) CWE-250 vulnerability in neuron-core/neuron-ai. A fix is available for neuron-core/neuron-ai — see the affected versions and patch details below.
Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
Exploitation Status
No confirmed exploitation observed yet
- CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
- CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.
Exploitation and automatability from CISA’s SSVC triage for GHSA-898v-775g-777c.
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
How urgent is this, really
GHSA-898v-775g-777c plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.
Where this sits among everything scored
Of 378,567 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.
Real-World Exposure
neuron-core/neuron-aiReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects Packagist packages — download data is not available via public APIs for these ecosystems.
Description
Impact
MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare() + execute() without semantic restrictions.
This is consistent with the name (“write tool”), but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause execution of destructive queries such as DROP TABLE, TRUNCATE, DELETE, ALTER, or privilege-related statements (subject to DB permissions).
Who is impacted: Deployments that expose an agent with MySQLWriteTool enabled to untrusted input and/or run the tool with a DB user that has broad privileges.
Patches
Not patched in: 2.8.11
Recommended improvements (even if keeping the tool intentionally powerful):
-
Provide a safer API that supports only constrained operations (e.g.,
insertRecord,updateRecord) with allowlisted tables/columns. -
Add a policy/allowlist layer (e.g., allow only
INSERT/UPDATEon selected tables; forbidDROP/TRUNCATE/ALTER/GRANT). -
Add optional review workflow: log + require human approval for high-risk statements; or “dry-run” mode.
-
Document strongly that the tool must not be exposed to untrusted prompts without additional safeguards.
Workarounds
-
Do not enable
MySQLWriteToolfor public/untrusted agents. -
Use a dedicated DB user with least privilege:
- no
DROP, noALTER, noGRANT, no access to sensitive tables unless necessary
- no
-
Add an application-layer policy rejecting high-risk statements (
DROP,TRUNCATE,ALTER,GRANT,REVOKE,CREATE USER, etc.). -
Implement authorization gating for tool calls (RBAC, allow tool use only for trusted operators).
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐘Packagist | neuron-core/neuron-ai | all versions | 2.8.12composer require neuron-core/neuron-ai:^2.8.12 |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for neuron-core/neuron-ai, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update neuron-core/neuron-ai to 2.8.12 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-898v-775g-777c is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like GHSA-898v-775g-777c can be triaged on real exposure rather than presence alone.
Tailored to GHSA-898v-775g-777c. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is GHSA-898v-775g-777c in your dependencies?
O3 Security finds GHSA-898v-775g-777c across Packagist dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.