ClawHub
Back to skill

Security audit

Shortcut

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Shortcut, but its setup instructions tell the agent to run unverified remote installer scripts if the CLI is missing.

Review this before installing. The Shortcut connector behavior is clearly described, but avoid letting an agent run the documented installer commands automatically; install the oo CLI only through a trusted, verified method and confirm any Shortcut create or update action before it runs.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:69
Finding

Unverified Remote Installation Scripts Executed Directly by Shells

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 69–73
Vulnerability Type: Remote payload retrieval and execution
Risk Level: High

Vulnerable Code

bash
curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
powershell
irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell

Technical Analysis

The installation instructions retrieve mutable scripts from external URLs and immediately execute them with Bash or PowerShell. They do not pin a script version, verify a cryptographic digest or signature, save the script for inspection, or otherwise establish that the downloaded content matches an audited release.

HTTPS protects content while it is in transit but does not eliminate the risks of a compromised hosting server, deployment pipeline, maintainer account, or signing infrastructure. Because the downloaded script can be changed after this Skill has been reviewed, its effective behavior is not bounded by the contents of the audited project.

Installing the oo CLI may support the Skill's declared Shortcut functionality, but direct execution of an unverified remote payload exceeds the minimum mechanism necessary for installation. A pinned and cryptographically verified package or artifact would provide a narrower trust boundary.

Attack Path

  1. The oo command is unavailable, causing the agent or user to consult the first-time setup instructions.
  2. An attacker compromises the external script host, its publishing pipeline, or an authorized publishing account.
  3. The attacker replaces install.sh or install.ps1 with a malicious payload.
  4. The documented command downloads the current payload without integrity or authenticity verification.
  5. Bash or PowerShell immediately executes the attacker-controlled content with the privileges of the invoking account.
  6. The payload can access resources available to that account and may install addi ...[truncated 753 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove the curl | bash and irm | iex installation patterns.
  2. Prefer a trusted platform package manager with a version-pinned package and documented publisher identity.
  3. If standalone artifacts are required, pin an explicit release version and download the installer to a local file rather than piping it directly into a shell.
  4. Publish a SHA-256 digest through an independently protected release channel and verify it before execution.
  5. Cryptographically sign release artifacts and require signature verification against a documented, pinned publisher key.
  6. Display or inspect the verified script before execution and require explicit user approval before installing software.
  7. Run installation with ordinary user privileges wherever possible; do not request administrator or root privileges unless a specific installation step demonstrably requires them.
  8. Document the files, executables, network endpoints, and configuration changes made by the installer so users can assess its scope.
  9. Keep the existing instruction not to install proactively, ensuring setup occurs only after a genuine missing-command failure and explicit user authorization.

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 the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This creates a supply-chain and remote code execution risk: if the remote host, transport, or script contents are compromised, arbitrary code will run immediately on the user's machine without review.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction to use this skill for "ANY Shortcut request" is overly broad and can cause the agent to route all Shortcut-related tasks through this skill without first considering narrower, safer, or more context-appropriate handling. In practice, this increases the chance of unintended invocation of write-capable actions, especially because the same skill exposes both read and state-changing operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.