ClawHub
Back to skill

Security audit

Catalyst Calendar

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only trading catalyst calendar skill that discloses its local file storage and shows no hidden code, credential access, exfiltration, or trade execution.

Install only if you want an agent-maintained trading catalyst calendar under ~/.openclaw/workspace/trading/. Review proposed additions before saving, verify event sources, and do not let downstream trading tools act automatically on these entries without human review.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description is broad enough that an agent may invoke it for generic market-event or planning requests without a clearly bounded trigger. That can cause unintended data collection or workflow activation, especially because the skill is tied to updating a persistent local calendar and downstream trading components.

Vague Triggers

Low
Confidence
84% confidence
Finding
The "Add new event" instruction uses open-ended phrasing and does not define validation, schema checks, or confirmation requirements before modifying the calendar. In an agent setting, vague update commands can lead to accidental writes, malformed entries, or insertion of untrusted event data into a persistent file.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The weekly scan workflow explicitly instructs updating a local file but does not warn that it modifies user data or require consent before doing so. This is risky because an agent could perform autonomous searches and persist changes to the user's workspace based on external information that may be incorrect, manipulated, or simply unwanted.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.