ClawHub
Back to skill

Security audit

NEXUS Cron Builder

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a simple cron-expression helper, but its artifacts add remote paid-service use, payment-proof handling, and ambiguous automatic invocation that users should review before installing.

Install only if you are comfortable with cron-related prompts being sent to a third-party paid endpoint and with configuring payment proof credentials. Prefer explicit confirmation before each remote/payment use, avoid sending sensitive schedule details, and consider an offline cron-expression tool if you do not need the hosted paid service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill for simple cron-expression generation requires a payment proof environment variable and embeds broad payment/authentication protocol support that is not functionally necessary for the advertised task. This expands the trust boundary, increases secret-handling risk, and can cause agents to transmit payment credentials to an external service for a low-risk utility capability.

Context-Inappropriate Capability

Low
Confidence
87% confidence
Finding
The documentation introduces unrelated AP2/XRPL batch-settlement and cross-skill payment orchestration details that are outside the cron-builder function. While not exploit code by itself, this increases attack surface and may normalize invoking broader payment capabilities from a narrowly scoped skill, creating confusion and opportunity for misuse.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The README states that the skill is 'automatically invoked' when a matching task is detected, but it does not define matching criteria, required user consent, or data-handling boundaries. In an agent ecosystem, ambiguous auto-invocation can cause unintended routing of user prompts and silent transmission of task content to a remote paid service, increasing the risk of privacy leakage and unauthorized actions.

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/cron-builder \
  -H "Content-Type: application/json" \
  -d '{"input": "your query here"}'
# Returns 402 + WWW-Authenticate: Payment header
Confidence
83% confidence
Finding
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/cron-builder \ -H "Content-Type: application/json" \ -d '{"input": "your query here"}' # Returns 402 + WWW-Authenticate:

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.