Back to skill

Security audit

Medici Investments — Market Pulse Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple market-summary guide with no bundled executable code, but its setup instructions are incomplete and use unpinned Python packages.

Install only in a virtual environment, avoid sudo/admin installation, and be aware that the documented market_pulse.py script is not present in this package. Treat outputs as informational market context, not financial advice or trading automation.

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
README.md:24
Finding

Unpinned Third-Party Dependencies Installed Without Integrity Verification

Content
View full analysis

Vulnerability Details

File Location: README.md, line 24
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

Vulnerable code snippet:

bash
pip install yfinance pandas

Technical Analysis

The installation command requests the latest available versions of yfinance and pandas without version constraints, cryptographic hashes, or a dependency lock file. Consequently, the installed code may differ between installations and cannot be matched against a reviewed dependency set.

Python package installation can execute package-controlled build or installation logic. If a requested package, one of its transitive dependencies, or the configured package repository is compromised, following this instruction may execute attacker-controlled code. The repository provides no lock file or hash manifest through which users can verify package integrity.

This finding does not establish that the named packages are currently malicious. The vulnerability is the project's reliance on mutable, unverified supply-chain inputs.

Attack Path

  1. An attacker compromises a requested package, a transitive dependency, or the package source configured in the user's environment.
  2. The attacker publishes a malicious release that satisfies the unconstrained dependency request.
  3. A user follows the documented Quick Start instructions and runs pip install yfinance pandas.
  4. pip resolves and downloads the attacker-controlled release because no reviewed versions or hashes are enforced.
  5. Malicious build, installation, or runtime code executes with the privileges of the user running pip.
  6. The payload can access or alter resources available to that account and can compromise the associated Python environment.

Impact Assessment

Successful exploitation could provide arbitrary code execution with the privileges of the installing user. The accessible scope may include files, credentials, enviro ...[truncated 308 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace the unconstrained installation command with a reviewed, version-pinned dependency manifest.

  2. Generate and distribute cryptographic hashes for every direct and transitive dependency.

  3. Require hash validation during installation, for example:

    bash
    python3 -m pip install --require-hashes -r requirements.txt
    
  4. Use a lock-generation tool such as pip-tools to produce reproducible dependency sets, and review updates before regenerating the lock file.

  5. Install dependencies inside an isolated virtual environment using an unprivileged account; explicitly warn users not to run the command with sudo.

  6. Configure trusted package indexes explicitly in controlled deployment environments and monitor dependencies for reported vulnerabilities or compromised releases.

  7. Add the documented scripts/market_pulse.py implementation to the package, or remove the execution instructions until the referenced script and its dependency requirements can be audited.

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown/manifest file includes an empty trigger_patterns list, so it does not specify what phrases or conditions should invoke the skill. Without explicit triggers or exclusion conditions, the activation boundary is unclear and could lead to unintended or inconsistent invocation behavior.

Content

No source excerpt is available for this finding.