ClawHub
Back to skill

Security audit

GIPHY

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for using GIPHY through OOMOL, but its first-time setup tells users to execute unverified remote installer scripts directly in a shell.

Before installing, use the skill's normal oo connector commands only after you already trust and have installed the OOMOL CLI. Avoid running the documented curl | bash or irm | iex installer commands directly; prefer an official signed or version-pinned installer, review the downloaded script first, and verify any checksum or publisher signature when available.

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 (2)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:69
Finding

Unverified Remote Installer Executed Through Bash

Content
View full analysis

Vulnerability Details

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

bash
curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux

Technical Analysis

The setup instructions download a shell script from an external URL and immediately pipe it into Bash. The effective code is not included in the reviewed project and can change after the Skill has been audited. No release version is pinned, and the command performs no cryptographic signature or checksum verification before execution.

Although installation is presented as a conditional response to an oo: command not found error and the hostname is consistent with the declared OOMOL service, HTTPS alone does not establish that the retrieved script is immutable or independently verified. Compromise of the remote hosting infrastructure, domain, deployment pipeline, or TLS trust chain could cause arbitrary attacker-controlled commands to execute. Installing the connector CLI may be necessary for the Skill, but executing an unverified mutable response directly from the network exceeds the minimum safe privilege required for that setup.

Attack Path

  1. The oo CLI is absent, causing an oo: command not found failure.
  2. The Agent or user follows the documented first-time setup instructions.
  3. An attacker compromises or gains the ability to modify the script returned by https://cli.oomol.com/install.sh, or otherwise compromises the delivery path.
  4. curl downloads the current response without pinning or integrity verification.
  5. The pipe sends the response directly to Bash without saving it for inspection.
  6. Bash executes the attacker-controlled commands with the permissions of the invoking account.

Impact Assessment

Successful exploitation provides arbitrary command execution with the privileges of the user running the installation command. The payload could read or ...[truncated 375 chars]

Remediation
View remediation

Remediation Suggestions

  • Remove the direct curl | bash installation pattern.
  • Direct users to a version-pinned release or an official platform package manager.
  • Download the installer to a local file without executing it automatically.
  • Publish a cryptographic signature and SHA-256 checksum through a separately protected channel, and verify both before execution.
  • Allow the user to inspect the downloaded script and require explicit confirmation before running it.
  • Pin the installer and CLI version so the reviewed artifact cannot silently change.
  • Run installation with ordinary user privileges and avoid requesting sudo unless a specific, documented operation requires it.
  • Prefer a package format that supports publisher-signature verification and reproducible provenance.

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:73
Finding

Unverified Remote Installer Executed Through PowerShell

Content
View full analysis

Vulnerability Details

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

powershell
irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell

Technical Analysis

The Windows setup command retrieves a mutable PowerShell script from an external service with Invoke-RestMethod (irm) and immediately evaluates the response with Invoke-Expression (iex). The project does not contain the executed code, pin a release, or verify an Authenticode signature or cryptographic digest.

This construction turns the remote response into a direct code-execution channel. The script may be replaced after this Skill is reviewed, and a compromise of the hosting account, release process, domain, or network trust path could substitute malicious PowerShell. While installing the declared CLI is related to the Skill’s functionality, immediate execution of an unverified network response is not the least-privilege or least-trust method of performing that installation.

Attack Path

  1. The oo CLI is unavailable on a Windows system.
  2. The Agent or user follows the documented PowerShell setup command.
  3. An attacker modifies the content delivered from https://cli.oomol.com/install.ps1 or compromises its delivery infrastructure.
  4. irm retrieves the attacker-controlled response without version pinning or integrity validation.
  5. The pipeline passes the response directly to iex.
  6. PowerShell evaluates the response as code under the invoking user’s security context.

Impact Assessment

Exploitation permits arbitrary PowerShell execution with the invoking account’s privileges. An attacker could access user-readable files and credentials, modify the user environment, download additional payloads, tamper with local tools, or configure user-level persistence. If the shell was already running with administrative privileges, the same path could le ...[truncated 100 chars]

Remediation
View remediation

Remediation Suggestions

  • Remove the irm | iex installation command.
  • Distribute the CLI as a version-pinned, Authenticode-signed installer or through a trusted Windows package repository.
  • Download the installation artifact to disk first rather than evaluating a web response.
  • Verify the publisher signature and a documented SHA-256 digest before execution.
  • Present the artifact and intended changes to the user and require explicit approval before installation.
  • Ensure the installer operates without administrator privileges unless a narrowly defined installation step requires elevation.
  • Publish immutable release URLs and maintain verifiable provenance for installation artifacts.

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
97% confidence
Finding

The skill instructs users to install software by piping a remotely fetched script directly into a shell, which creates a supply-chain and remote code execution risk. If the install endpoint, transport path, or upstream distribution is compromised, arbitrary code would execute immediately on the user's machine without prior inspection.

Content

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description says to use this skill for "ANY GIPHY request" and "Whenever a task involves GIPHY," which is very broad and lacks constraints or exclusion examples. This can overlap with ordinary mentions of GIPHY and does not clearly define when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.