Back to skill

Security audit

huaweicloud-vpc-subnet-list

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly coherent read-only Huawei Cloud subnet lister, but it has a real endpoint-validation flaw that can send signed credential metadata to a host chosen through the region setting.

Review this skill before installing. Use only a trusted config file, do not accept region values from untrusted input, and restrict the Huawei Cloud AK/SK to the documented read-only permissions. The region validation flaw should be fixed before using this in automated or shared workflows.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
list_subnets.py:33
Finding

Unvalidated Region Value Allows Credential-Bearing Requests to Attacker-Controlled Hosts

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill declares Python and describes reading local credential files and making outbound cloud API requests, but it does not define an explicit tool scope such as allowed-tools or permissions. Without a restrictive scope, an agent runtime may grant broader file and network capabilities than intended, increasing the chance of unintended credential access or misuse of network operations beyond the stated read-only purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example uses Chinese-only natural-language descriptions for the Access Key and Secret Access Key fields. For a general configuration file, this imposes a specific language without any visible opt-in or justification, which fits the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file’s natural-language instructions and warnings are entirely in Chinese, and there is no indication that the skill is region-specific or that users can opt into this locale. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains natural-language comments/docstrings written only in Chinese, indicating a fixed language assumption for the skill's user-facing or maintainer-facing guidance. Under the stated policy, forcing a specific language without user opt-in is a locale/language policy violation unless the constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Multiple natural-language strings in the file, including this docstring, are Chinese-only and do not indicate that the language choice is optional or region-specific by design. That creates a natural-language policy concern because the skill appears to impose a language without documenting user choice or justification.

Content

No source excerpt is available for this finding.