ClawHub
Back to skill

Security audit

Productboard

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Productboard read/search integration using OOMOL's oo CLI, with a broad routing phrase but no hidden or unrelated behavior found.

Install this only if you trust OOMOL's connector and want the agent to read Productboard workspace data. For ambiguous Productboard tasks or any future action tagged write or destructive, require explicit confirmation before running it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description says to use this skill for ANY Productboard request, which creates an overly broad routing rule for an external-service skill. That can cause the agent to invoke the skill in situations where direct handling, stricter scoping, or additional user confirmation would be safer, increasing the chance of unnecessary data exposure or unintended access to workspace information.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.