Back to skill

Security audit

Ai Intelligent Contract Review

Security checks for vulnerabilities and agentic risk

Overview

The skill describes a coherent contract-review tool, but its install steps tell users to download and run unaudited remote code from a mutable GitHub repository.

Install only if you trust the external repository and are comfortable reviewing or sandboxing the code before running it. Do not process confidential, privileged, personal, or business-critical contracts unless you understand where the documents are stored, how model processing works, and how data can be deleted or controlled.

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:39
Finding

Mutable Remote Payload Retrieval and Execution

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 39-42
Vulnerability Type: Remote payload retrieval and unsafe dependency installation
Risk Level: High

Vulnerable Code

bash
git clone https://github.com/openclaw-skills/ai-intelligent-contract-review
cd ai-intelligent-contract-review
pip install -r requirements.txt
python app.py

Technical Analysis

The installation instructions direct users to clone a mutable external Git repository, install the dependencies declared by that repository, and execute its application. The reviewed package does not contain the referenced requirements.txt, app.py, or any implementation that would allow the effective payload and dependency set to be audited.

Because the command does not pin the repository to a verified commit or release, its contents can change after this skill package has been reviewed. Moreover, pip install may execute package build or installation logic, while the subsequent python app.py command directly executes the remotely obtained application.

This constitutes remote payload retrieval and execution. It also creates an insecure dependency chain because package names, versions, hashes, and installation behavior cannot be verified from the submitted artifact.

Attack Path

  1. An attacker compromises the referenced repository, its maintainer account, or an included dependency.
  2. The attacker modifies app.py, requirements.txt, or a dependency installation script to contain malicious code.
  3. A user follows the documented installation instructions and clones the current mutable repository state.
  4. pip install -r requirements.txt installs the attacker-controlled dependency set and may execute malicious build-time code.
  5. The user runs python app.py, directly executing the remotely supplied payload.
  6. The payload operates with the privileges of the user performing the installation.

Impact Assessment

Succe ...[truncated 660 chars]

Remediation
View remediation

Remediation Suggestions

  1. Include the complete application, dependency manifest, and relevant installation files in the reviewed skill artifact.
  2. If external retrieval is necessary, pin the repository to an immutable, reviewed commit hash rather than cloning the default branch.
  3. Verify downloaded content using cryptographic signatures or published checksums before installation or execution.
  4. Pin all Python dependencies to exact versions and require cryptographic hashes, such as through a lock file or pip install --require-hashes.
  5. Review transitive dependencies and obtain packages only from explicitly trusted registries.
  6. Avoid immediately executing remotely downloaded applications. Require a separate verification and approval step.
  7. Perform installation and execution in an isolated, least-privileged environment without production credentials or sensitive filesystem access.
  8. Ensure the documented author and repository ownership are verified before directing users to the external source.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill describes automated contract review, comparison, generation, reminders, and archival, all of which imply handling highly sensitive legal and business data, but it provides no warning about confidentiality, retention, access control, or model-processing risks. This can lead users to submit contracts containing trade secrets, personal data, or privileged information without informed consent or appropriate safeguards.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and the entire markdown content are written in Chinese, which effectively forces a specific language experience. The file does not state that the skill is intended only for Chinese-speaking users or provide any opt-in or alternative language support.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description text on L04 is exclusively Chinese, which can imply a fixed language experience without any stated opt-in or explanation of locale scope. Under the language/locale policy check, this is a natural-language policy concern because users are not told that the skill is Chinese-only or offered an alternative.

Content

No source excerpt is available for this finding.