ClawHub
Back to skill

Security audit

Clerk

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Clerk through OOMOL, but its setup guidance includes unverified remote installer commands that can execute code on the user's machine.

Review the oo CLI installation path before installing. Prefer installing the CLI from a verified package or documented release with integrity checks, and require explicit user approval before any write or destructive Clerk action such as banning, locking, updating, or deleting users.

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 tells the agent to install software via curl ... | bash, which executes a remotely fetched script without verification, pinning, or integrity checks. Because skill content is untrusted and may be triggered in automation contexts, this creates a direct path to arbitrary code execution if the remote host, network path, or installer content is compromised.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description instructs the agent to use this skill for ANY Clerk-related request, creating an overly broad routing rule that can capture sensitive read, write, and destructive operations without narrowing by user intent or risk level. In context, this increases the chance of unsafe delegation and accidental execution of high-impact account actions such as banning, locking, updating, or deleting users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.