Back to skill

Security audit

futbol-libre-hoy

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but it tells agents to run unpinned third-party packages from package registries for a simple live-score lookup.

Install only if you are comfortable letting the futbol-libre-hoy npm or Python package run with your normal local permissions. Prefer a pinned, reviewed version with hashes or a locked dependency workflow, and avoid running it in an environment containing sensitive files or credentials until the package provenance is verified.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:12
Finding

Unpinned Third-Party Packages Are Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 12–20
Vulnerability Type: Unpinned npm and Python package execution
Risk Level: Medium

Vulnerable Code

bash
npx futbol-libre-hoy
npx futbol-libre-hoy --live
npx futbol-libre-hoy --date YYYY-MM-DD
npx futbol-libre-hoy --json

Python alternative:

bash
pip install futbol-libre-hoy
futbol-libre-hoy --live

Technical Analysis

The skill directs users or agents to resolve and execute the third-party futbol-libre-hoy package without specifying a reviewed version, cryptographic hash, lockfile, or verified source repository.

npx futbol-libre-hoy may download the currently published npm package and execute it immediately. The Python alternative similarly installs the mutable package currently associated with that name on the configured package index and then runs its executable.

Consequently, the effective code executed by these instructions can change after the skill itself has been reviewed. If the package, one of its transitive dependencies, the publisher account, or the relevant registry entry is compromised, following the documented commands could execute attacker-controlled code. The package source is not included in the audited project, so its implementation and dependency chain could not be verified.

Attack Path

  1. An attacker compromises the package publisher, a transitive dependency, or the relevant registry package entry.
  2. The attacker publishes a malicious release under the expected package name or causes a malicious dependency version to be resolved.
  3. A user or agent follows the commands in SKILL.md.
  4. npx downloads and immediately executes the mutable npm package, or pip installs the mutable Python package before its CLI is executed.
  5. Malicious package code runs with the operating-system permissions of the invoking user or agent process.

Impact Assessment

Successful exploitation co ...[truncated 516 chars]

Remediation
View remediation

Remediation Suggestions

  • Pin each dependency to a specific, reviewed version rather than resolving the latest registry release.
  • Commit appropriate lockfiles and retain registry integrity metadata.
  • For Python installations, require hashes through a locked requirements file, such as pip install --require-hashes -r requirements.txt.
  • Avoid implicit package downloads through bare npx commands. Install an approved, pinned package version through a controlled setup process and invoke the verified local binary.
  • Document the authoritative package registry and source repository so package identity can be independently verified.
  • Review the package, installation hooks, executable entry points, and transitive dependency graph before approval.
  • Consider vendoring the reviewed implementation or distributing a signed artifact with a published checksum.
  • Run the CLI with least privilege in a restricted environment, without unnecessary credentials or access to sensitive files.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill instructs users to run npx futbol-libre-hoy without pinning a specific package version. This allows whatever version is currently published under that package name to be fetched and executed at runtime, creating a supply-chain risk if the package is updated maliciously or compromised. Because npx executes remote package code directly, the exposure is real rather than theoretical.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

This command uses npx futbol-libre-hoy --live without a pinned version, so users may execute newly published code implicitly. If the npm package is hijacked, typo-squatted, or later updated with malicious behavior, the skill would direct users to run that code immediately. The live-scores context does not reduce the execution risk because the command still fetches and runs code from the registry.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The --date example still invokes an unpinned npm package through npx, which means arbitrary future package contents may be executed. Any compromise of the package publisher account or package ownership could turn this benign-looking data retrieval command into a delivery mechanism for malicious code.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The --json example also runs npx futbol-libre-hoy without version pinning, exposing users to supply-chain attacks through registry-side changes. Since npx downloads and executes code on demand, the skill effectively trusts the latest published package at execution time, which is unsafe for security-conscious environments.

Content

No source excerpt is available for this finding.