ClawHub
Back to skill

Security audit

NEXUS Text To Sql

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed paid remote text-to-SQL service, with network and payment use aligned to its stated purpose and no local file, shell, or persistence behavior found.

Install only if you are comfortable sending text-to-SQL prompts and payment proof data to the NEXUS hosted service. Avoid including credentials, personal data, proprietary schema details, or sensitive records unless your organization has approved that external processing and payment flow.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Skill Enumeration

Medium
Category
Agent Snooping
Content
Or manually copy the `SKILL.md` to your OpenClaw skills directory:

```bash
cp SKILL.md ~/.openclaw/skills/nexus-text-to-sql/SKILL.md
```

## Usage
Confidence
80% confidence
Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The README states the skill is 'automatically invoked' when a matching task is detected, but it does not define trigger boundaries, approval requirements, or data-handling limits. In a text-to-SQL context, ambiguous auto-invocation can cause users or agents to send sensitive natural-language prompts to a remote paid service unexpectedly, increasing the risk of unintended data disclosure and surprise external actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README describes usage of a hosted API but does not clearly warn that natural-language input is transmitted to a third-party remote service. For a text-to-SQL tool, prompts may contain schema details, credentials, business logic, or sensitive records, so the lack of a prominent disclosure materially increases the chance of inadvertent exfiltration.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# Step 1: Get the x402/MPP challenge
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/text-to-sql \
  -H "Content-Type: application/json" \
  -d '{"input": "your query here"}'
# Returns 402 + WWW-Authenticate: Payment header
Confidence
93% confidence
Finding
The README explicitly instructs users to POST input to an external hosted endpoint, which means user data leaves the local environment. External transmission is expected for a SaaS-backed skill, but in this context it is still a real security concern because text-to-SQL inputs can contain sensitive business data, and the README does not pair the example with adequate warnings or minimization guidance.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill advertises a broad capability to convert arbitrary natural language into SQL without defining trigger constraints, database scope, or safety boundaries. In agent ecosystems, this can cause over-invocation on sensitive prompts and may facilitate unsafe downstream use such as generating destructive, privacy-impacting, or policy-bypassing SQL against connected databases.

External Transmission

Medium
Category
Data Exfiltration
Content
### API Call

```bash
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/text-to-sql \
  -H "Content-Type: application/json" \
  -H "X-Payment-Proof: $NEXUS_PAYMENT_PROOF" \
  -d '{
Confidence
94% confidence
Finding
The skill explicitly instructs agents to transmit user input and a payment proof header to an external third-party endpoint. This creates a real data exfiltration boundary: sensitive prompts, schema details, business data, or tokens may leave the local trust domain, and the trust statement does not technically enforce minimization, redaction, or destination validation.

Static analysis

No suspicious patterns detected.