ClawHub
Back to skill

Security audit

Onfleet

Security checks for vulnerabilities and agentic risk

Overview

This Onfleet connector is mostly coherent, but it includes remote pipe-to-shell installation steps and can change or delete Onfleet task data, so users should review it before installing.

Install only if you trust OOMOL as the connector provider and are comfortable with an agent using your connected Onfleet account. Manually install or verify the oo CLI instead of allowing unattended pipe-to-shell setup, and require explicit confirmation before any create, update, complete, or delete action in Onfleet.

A.I.G

Vulnerability Patterns
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 a shell (curl ... | bash). This creates a code-execution path where a compromised host, CDN, DNS path, or vendor endpoint could deliver arbitrary commands, and the skill context makes it more dangerous because it normalizes this fallback during operation of a third-party integration.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L03 says to use this skill for "ANY Onfleet request" and "Whenever a task involves Onfleet," which is a very broad activation condition without scope limits or exclusion examples. This can overlap with many routine mentions of Onfleet and may cause unintended invocation because it does not clearly define when the skill should or should not be used.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.