Skills

The skill facilitates high-privilege identity management and executes unauthorized network and shell commands, creating significant risks for privilege escalation, data exfiltration, and uncontrolled agent recursion.

The skill executes unverified remote scripts via shell pipes, performs unauthorized file writes, and processes untrusted external content, creating significant risks for arbitrary code execution and system compromise.

The skill insecurely downloads and executes unverified remote scripts directly into a shell, creating a critical vulnerability that allows for arbitrary code execution and system compromise.

The skill insecurely executes unverified remote code via direct shell piping, granting external servers arbitrary control over the agent's environment without integrity checks or version pinning.

The skill executes unverified remote code via shell piping and establishes unauthorized network connections, posing a critical risk of arbitrary command execution and data exfiltration.

This skill executes unverified remote code, performs unauthorized file exfiltration, and uses unpinned dependencies, posing a critical risk of arbitrary code execution and data theft.

The skill executes unverified remote scripts via insecure shell piping and performs unauthorized network operations, creating a critical risk of arbitrary code execution and persistent system compromise.

The skill forces the execution of unverified remote scripts to install dependencies, creating a critical supply chain vulnerability that enables arbitrary code execution and potential credential harvesting.

This skill executes unverified remote code, exposes sensitive API keys in logs, and provides an administrative bypass that renders its mandatory authorization controls ineffective.

The skill mandates an insecure curl-to-bash installation pattern that executes unverified remote scripts with system privileges, creating a critical risk of arbitrary code execution.

The skill executes arbitrary shell commands and promotes insecure supply chain practices by installing unverified, unpinned global dependencies while lacking proper documentation and licensing.

The skill executes unverified, remote shell scripts via insecure piping, creating a critical supply chain vulnerability that allows for arbitrary code execution and system compromise.

The skill executes arbitrary code by piping unverified remote scripts directly into a shell, creating a critical vulnerability that allows for unauthorized system access and remote command execution.

The skill facilitates supply chain attacks by executing unverified remote code and lacks necessary security declarations for its network access and tool usage, posing a critical risk.

This skill executes unpinned, arbitrary code from the npm registry and performs unauthorized network and file operations without declaring necessary security constraints or tool permissions.

This skill executes arbitrary shell commands and installs unverified packages while explicitly bypassing human oversight, creating critical risks of remote code execution and credential exfiltration.

The skill forces the execution of unverified remote scripts via insecure curl-to-bash patterns, exposing the agent to arbitrary code execution and supply chain attacks.

The skill forces the installation of unverified third-party binaries and executes remote scripts directly in a shell without integrity checks, creating a critical risk of arbitrary code execution.

The skill executes unverified remote code and performs unauthorized network and file operations without declaring necessary tool constraints, posing a critical risk of arbitrary command execution.

This malicious skill masquerades as an agent orchestrator to exfiltrate sensitive API keys, execute unverified remote code, and expose the host environment through insecure, unauthenticated network configurations.

The skill executes arbitrary remote code by piping unverified scripts directly into a shell, bypassing security controls and creating a critical vulnerability for remote command execution.

The skill executes arbitrary remote code via insecure curl-to-bash installation and lacks necessary tool declarations, creating a critical risk of unauthorized system access and remote command execution.

The skill is malicious because it executes destructive shell or Java runtime commands, posing a critical risk to system integrity and security.

This skill executes unverified remote code and performs unauthorized network operations while lacking necessary security constraints, creating significant risks for arbitrary command execution and large-scale spam abuse.

This skill executes unverified remote code, exfiltrates local files without consent, and uses unpinned dependencies, creating a severe risk of arbitrary code execution and credential theft.

The skill executes unverified remote code via shell pipes and performs unauthorized network operations without declaring necessary tool permissions, creating a critical risk of arbitrary code execution.

The skill executes unverified remote code via shell pipes, bypasses critical user confirmation prompts, and lacks necessary tool constraints, creating a high risk of arbitrary command execution and system compromise.

The skill executes unverified remote code via shell pipes and lacks necessary tool constraints, creating critical vulnerabilities for arbitrary code execution and unauthorized system access.

The skill executes unverified remote code via insecure shell piping and uses unpinned package dependencies, creating critical vulnerabilities for arbitrary code execution and supply chain compromise.

This skill poses a critical security risk by executing arbitrary remote scripts, bypassing read-only constraints via unauthorized API calls, and performing unconstrained network and system operations without proper security declarations.

The skill performs unauthorized dynamic code execution and network access while using keyword stuffing to manipulate discovery, all while bypassing security constraints by failing to declare its tool surface.

This skill facilitates arbitrary remote code execution, insecurely handles authentication tokens, and lacks necessary security constraints, creating significant risks for system compromise and unauthorized data access.

This skill facilitates remote code execution, mandates insecure credential handling, and uses deceptive social engineering to trick users into granting escalated permissions and executing unverified, external malicious payloads.

The skill performs unauthorized remote code execution and network access while lacking declared tool constraints and essential documentation, posing a significant security risk through opaque, unverified runtime behavior.

The skill executes unverified remote scripts directly into a shell and encourages insecure handling of API keys, creating significant risks for arbitrary code execution and credential exposure.

This skill executes arbitrary commands, exposes hardcoded credentials, lacks necessary security declarations for network and tool access, and contains vulnerabilities to supply chain and cross-site scripting attacks.

The skill bypasses human-in-the-loop controls for infrastructure changes, insecurely handles sensitive API keys, and executes unconstrained network and system operations without declaring required tool permissions.

The skill performs unauthorized remote code execution and network access while bypassing security constraints by failing to declare its tool surface and capabilities.

This skill executes unauthorized shell commands and systematically bypasses mandatory user confirmation protocols to perform potentially destructive actions without human oversight.

This skill executes dangerous, unverified bash scripts via SSH while actively bypassing mandatory user confirmation, creating a high risk of command injection and unauthorized system manipulation.

This skill executes unverified remote code, exfiltrates local files, and uses opaque binaries to bypass security oversight while posing as a legitimate tool to harvest user credentials.

The skill executes arbitrary remote code and insecurely manages sensitive credentials while bypassing security constraints by failing to declare its network and file system tool permissions.

This skill functions as a malicious exploitation toolkit that instructs the agent to perform destructive SQL injections, exfiltrate credentials, and execute unauthorized reverse shells against target systems.

This skill is malicious, containing a reverse shell and unauthorized environment access, while also suffering from critical vulnerabilities including arbitrary file read, command injection, and unpinned dependency execution.

This skill executes unverified remote code, disables critical authentication mechanisms, leaks sensitive dashboard tokens, and performs unauthorized network and system operations without declaring necessary security constraints.

The skill executes arbitrary remote code from an external URL and performs unauthorized network and file operations without declaring necessary tool permissions, posing a critical remote execution risk.

The skill facilitates remote code execution and prompt injection via untrusted GitHub issues while exposing sensitive API keys and bypassing security constraints through undeclared tool and network access.

This skill masquerades as an AI app runner to perform unauthorized remote code execution, arbitrary file exfiltration, and credential harvesting via unpinned dependencies and opaque third-party CLI tools.