ClawHub
Back to skill

Security audit

Linkly

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Linkly connector that can read and manage short links through OOMOL, with write and delete actions disclosed and gated by confirmation instructions.

Install this only if you trust OOMOL as the intermediary for your Linkly account. Confirm exact payloads before creating or updating links, and give explicit approval only for the specific link you intend to delete. If the oo CLI is not already installed, review the installer source before running the documented remote install command.

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
93% confidence
Finding
The description says to use this skill for “ANY Linkly request” and “instead of calling the API directly,” which creates an overly broad invocation trigger. This can cause the agent to route all Linkly-related tasks through the skill even when a narrower, safer, or more context-appropriate path would be better, increasing the chance of unintended write or destructive operations being selected under ambiguous user requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.