Back to skill

Security audit

Test Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Huawei Cloud CCE cluster-listing helper, with normal cloud credential and SDK risks but no evidence of hidden or destructive behavior.

Install dependencies in a virtual environment, prefer pinned reviewed versions, provide only least-privilege Huawei Cloud credentials with cce:cluster:list permission, and inspect any external or separately supplied script before running it because the referenced script is not included in this artifact.

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:43
Finding

Unpinned Python dependencies create a mutable software supply-chain risk

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 43
Vulnerability Type: Unpinned third-party dependencies
Risk Level: Medium

bash
pip install huaweicloudsdk-cce huaweicloudsdk-core

Technical Analysis

The documented installation command installs huaweicloudsdk-cce and huaweicloudsdk-core without fixed versions or package hashes. As a result, the packages and their transitive dependencies are resolved dynamically from the package index configured on the user's system.

The reviewed dependency contents can therefore differ from the versions installed later. If a package release, transitive dependency, package-index account, or configured index is compromised, pip may retrieve attacker-controlled content. Depending on the selected distribution and build process, malicious code could execute while a source distribution is built or when the installed package is subsequently imported.

The project also instructs users to configure Huawei Cloud access credentials. Consequently, malicious dependency code executing in the same process or user environment may be able to read those environment variables.

Attack Path

  1. An attacker compromises a future release of a listed package, one of its transitive dependencies, or a package source trusted by the victim.
  2. A user follows the documented prerequisite and runs the unpinned pip install command.
  3. pip resolves the compromised version because no reviewed version or integrity hash is required.
  4. Attacker-controlled code executes during package building, installation, or a later package import.
  5. The code operates with the privileges of the user running pip or the Skill and can access resources available to that account.
  6. If Huawei Cloud credentials have been exported into the same environment, the malicious code may read and disclose them.
  7. Stolen credentials could then be used within the permissions assigned to the associated Huawei ...[truncated 627 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin every direct dependency to an explicitly reviewed version, for example:
    text
    huaweicloudsdk-cce==<reviewed-version>
    huaweicloudsdk-core==<reviewed-version>
    
  2. Generate and commit a lock file containing all transitive dependencies.
  3. Require package hashes during installation, such as through a hash-locked requirements file and pip install --require-hashes.
  4. Use only an explicitly configured, trusted package index. Consider an internally controlled package mirror containing approved artifacts.
  5. Review dependency updates before changing pinned versions and use automated vulnerability and provenance checks.
  6. Install dependencies in an isolated virtual environment under a non-privileged account; do not run pip as root.
  7. Avoid exposing cloud credentials during dependency installation. Provide credentials only to the final runtime process after all packages have been installed and verified.
  8. Apply least-privilege IAM permissions and rotate credentials immediately if dependency compromise is suspected.
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.