Back to skill

Security audit

华为云 ECS 实例列表查询

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-only Huawei Cloud ECS listing tool, with the main caution being user-managed plaintext cloud credentials.

Install only if you are comfortable creating a local config.json with Huawei Cloud AK/SK credentials. Use a dedicated read-only Huawei Cloud credential, set restrictive file permissions such as owner-only access, avoid sharing or archiving the skill directory with config.json, and rotate the credential if it may have been exposed.

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

Warning
Location
list_ecs.py:212
Finding

Long-Lived Cloud Credentials Stored in a Plaintext Configuration File

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 (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill invokes Python code that reads a local config file containing cloud credentials and makes outbound network requests to Huawei Cloud APIs, but the manifest does not declare any explicit tool scope such as allowed-tools or permissions. This weakens least-privilege and transparency guarantees: an agent or reviewer cannot easily constrain or validate the skill's access boundaries, increasing the risk of unintended file access or broader network use if the implementation changes or is abused.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language instructions, errors, and CLI help text exclusively in Chinese, which effectively forces a specific language for users. Under the policy, locale or language constraints should either be optional/opt-in or clearly justified as region-specific; that justification is not present in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This JSON example uses Chinese-only natural-language strings for the Access Key and Secret Access Key placeholders. Because the file provides no alternative language option or documented locale constraint, it can violate a language/locale policy requiring user choice or neutral defaults.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This test file includes natural-language strings and comments exclusively in Chinese, indicating the associated skill behavior and messaging are localized to a specific language by default. Under the policy, forcing a specific language without user opt-in or documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The asserted output string "暂无 ECS 实例" shows the skill returns Chinese-only user-facing text. Because no language choice or justification is present in this file, this appears to enforce a specific locale contrary to the stated policy guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The asserted error text "认证失败" indicates Chinese-only user-visible error messaging. Without any user opt-in or documented locale limitation, this is a language policy violation under the provided rules.

Content

No source excerpt is available for this finding.