ClawHub
Back to skill

Security audit

Cuttly

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for using Cuttly through OOMOL, but its setup instructions include unverified remote install commands that could execute arbitrary local code.

Review the OOMOL CLI installation method before installing. Prefer an official, version-pinned installer or a manually reviewed download instead of running the pipe-to-shell commands directly. Once installed, the skill's normal Cuttly actions are narrow, and write actions should be confirmed before execution.

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 installation command that fetches and executes a remote script directly from the network. If the remote host, transport path, or script content is compromised, users could execute arbitrary code on their machine; embedding this in a skill increases the chance an agent or user will follow it without independent verification.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description instructs agents to use this skill for "ANY Cuttly request," which is a very broad activation condition and does not define boundaries or exclusions. In a manifest/markdown context, this can cause unintended invocation for loosely related mentions of Cuttly because no negative examples or scope constraints are provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.