Back to skill

Security audit

huawei-cloud-cse-engine-list

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its environment-controlled command settings could run arbitrary programs with the process's cloud credentials, and a pagination flaw may return an incomplete inventory; the scan was partial.

Treat this as a review item and consider avoiding installation until the environment-controlled command overrides and incomplete pagination risk are addressed. The scan covered all nine listed components, but its analysis was marked partial because two local references could not be resolved; the AIG scan completed with no reported findings, which does not remove the concerns found by Skillspector.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (6)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/list_cse_engines.py (reported line 305)May include surrounding context.

python
cmd.extend(extra)
    cmd.extend(argv)
    try:
        proc = subprocess.run(
            cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
            timeout=120, universal_newlines=True,
        )

Tainted flow: 'cmd' from os.environ.get (line 299, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
86% confidence
Finding

CSE_LIST_HCLOUD_BIN selects an arbitrary executable, while CSE_LIST_HCLOUD_ARGS supplies unchecked arguments before the supposedly fixed operation, bypassing both operation guards. If an attacker can influence the agent's inherited environment, these test hooks permit arbitrary execution with the process's cloud credentials and privileges; this is not shell injection through normal CLI selectors and requires environment control.

Content

Scanner excerpt · scripts/list_cse_engines.py (reported line 305)May include surrounding context.

python
cmd.extend(extra)
    cmd.extend(argv)
    try:
        proc = subprocess.run(
            cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
            timeout=120, universal_newlines=True,
        )

SDK pagination can return an incomplete inventory despite a reported total indicating more engines.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The SDK loop stops on any short page even when the reported total indicates that more engines remain. In this inventory and version-audit skill, a successful but incomplete result can omit vulnerable or unexpected engines and give downstream security checks false assurance, although it does not itself grant access or modify resources.

Content

No source excerpt is available for this finding.

Acceptance criteria require Chinese-language user-facing hints without a documented language choice or opt-in.

Low
Category
Output Handling
Confidence
93% confidence
Finding

The criteria prescribe specific Chinese messages for empty results and authorization failures. No language choice, user opt-in, or justification for requiring Chinese output is provided.

Content

No source excerpt is available for this finding.

The module promises never to read secrets itself, but the SDK fallback explicitly reads AK/SK credentials.

Low
Category
Excessive Agency
Confidence
100% confidence
Finding

The module documentation at L011–L013 states that the script never reads secrets itself. However, L627–L632 reads credential values directly from the environment, and L668–L678 passes them into BasicCredentials. Credential access is justified for the SDK fallback, but the stated secret-handling assurance directly contradicts the implementation.

Content

No source excerpt is available for this finding.