ClawHub
Back to skill

Security audit

Zylvie

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Zylvie connector workflow with clear user-confirmation rules for write and destructive actions, though its CLI install fallback deserves caution.

Install only if you intend to manage Zylvie through OOMOL. Review any write or destructive payload before approving it, and use OOMOL's official installation documentation rather than blindly running pipe-to-shell installer commands when possible.

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 users to install the CLI via a remote script piped directly into a shell (curl ... | bash), which executes network-fetched code without inspection or integrity verification. If the hosting endpoint, transport, or distribution pipeline is compromised, this can lead to arbitrary code execution on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description instructs invocation for any task involving Zylvie, including reading, creating, updating, and deleting data. This is a very broad activation condition and does not provide exclusions or narrower constraints, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.