ClawHub
Back to skill

Security audit

skill-h-meeting-sync

Security checks across malware telemetry and agentic risk

Overview

This skill is purpose-aligned meeting automation, but it runs on a cron schedule with broad Gitea mutation authority and exposes meeting invite data, so it should be reviewed before installation.

Install only with a tightly scoped Gitea bot token and preferably an explicit repository allowlist. Treat command output as sensitive because it can include attendee emails and meeting join links. Review the cron configuration, archive behavior, and setup.sh before enabling automatic runs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly instructs the agent to run shell commands, read configuration from a local .env path, and call external services, yet it declares no permissions. In a cron-triggered automation context, this creates a real least-privilege and transparency gap: operators may not realize the skill can access local secrets, execute commands, and perform network actions that modify repositories and send email.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script emits attendee email addresses and meeting join URLs in its JSON output for all active meetings across managed repositories. In a backend cron context, this creates a clear data-exposure risk because downstream logs, task outputs, or other consumers may receive sensitive meeting metadata and PII without any minimization or access control at this layer.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
main.js:26