ClawHub
Back to skill

Security audit

Kenjo

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Kenjo through OOMOL, but it includes an unverified remote shell installer and can change or delete Kenjo business data, so it warrants review before use.

Install only if you trust OOMOL as the intermediary for Kenjo access, are comfortable with agents using your connected Kenjo account, and can review or replace the remote installer with a safer official installation method. Confirm all write or delete payloads carefully before allowing them to run.

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 includes a curl ... | bash pattern that fetches and executes a remote script directly, which is a classic supply-chain and remote code execution risk. Because this appears in setup guidance for a tool the agent may instruct users to run, a compromised host, CDN, or install endpoint could lead to arbitrary code execution on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description instructs the agent to use this skill for ANY Kenjo request, including broad reading, creation, updating, and deletion flows. That overly broad routing can trigger the skill in routine or ambiguous Kenjo-related conversations, increasing the chance of unintended tool use and, in this case, exposing users to state-changing and destructive actions through a single catch-all skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.