ClawHub
Back to skill

Security audit

Raisely

Security checks across malware telemetry and agentic risk

Overview

This skill is a purpose-built Raisely connector with disclosed read, write, and webhook deletion actions plus explicit confirmation requirements for state-changing operations.

Install this only if you intend to let the agent operate your Raisely account through OOMOL. Review payloads carefully before approving webhook creation, updates, or deletion, and make sure you trust the oo CLI/OOMOL connection used to broker credentials.

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
94% confidence
Finding
The skill description says to use this skill for ANY Raisely request, including reading, creating, updating, and deleting data. That broad routing instruction can cause the agent to invoke this powerful integration in situations where a narrower, more specific skill or extra confirmation logic would be safer, increasing the chance of unintended access or state-changing actions. The risk is elevated here because the skill includes write and destructive operations against a live third-party service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.