ClawHub
Back to skill

Security audit

Userflow

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for Userflow operations, but its fallback setup tells users to execute remote installer scripts directly without verification or explicit approval.

Review the setup instructions before installing. Prefer an official package-manager or manually reviewed installer flow for the oo CLI, and require explicit approval before any Userflow write or delete operation.

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 recommends installing software via curl ... | bash, which executes a remote script directly without prior verification. If the remote host, transport chain, or published installer is compromised, this can lead to arbitrary code execution on the user's machine. In this skill context, the danger is increased because the command is presented as an operational fallback step that an agent may surface during troubleshooting.

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 uses the phrase "for ANY Userflow request" and says "Whenever a task involves Userflow, use this skill," which is a very broad trigger condition. It does not define boundaries, exclusions, or negative examples, so ordinary references to Userflow could unintentionally activate the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.