ClawHub
Back to skill

Security audit

TRIGGERcmd

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for using TRIGGERcmd, but its first-time setup includes directly executing a remote installer, which needs review before use.

Install only if you are comfortable with OOMOL mediating TRIGGERcmd actions and with reviewing setup manually. Before running the documented installer, prefer an official verified package or inspect and verify the installer yourself; confirm every trigger_command request because it can run saved commands on your connected computer.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:56
Finding

Unverified Remote Installation Scripts Executed Directly by Shells

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install software by piping a remote script directly into bash, which is a classic supply-chain and remote code execution risk. If the install server, DNS, TLS trust chain, or the script itself is compromised, the agent would execute attacker-controlled code on the host with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description says to use this skill for ANY TRIGGERcmd request, which creates an overly broad routing trigger and can cause the agent to invoke this skill whenever TRIGGERcmd is mentioned, even when the user did not intend tool execution. In an agent setting, overbroad invocation increases the chance of unintended reads or, after insufficient confirmation, write actions such as triggering commands on connected computers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.