Back to skill

Security audit

Huawei Cloud ECS Detail Query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent read-only Huawei Cloud ECS query tool, but its installation and credential guidance create review-worthy security risk.

Review this skill before installing. Use a pinned and verified Huawei Cloud CLI installer if available, run installers without elevated privileges, prefer least-privilege read-only IAM credentials, avoid placing long-lived AK/SK values directly in shell history, and understand that hcloud configuration may persist credentials locally.

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

Warning
Location
SKILL.md:50
Finding

Unverified Remote Installer Retrieved from a Mutable URL and Executed

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (17)

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.

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.

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
70% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · huawei_cloud_ecs_detail_query.py (reported line 34)May include surrounding context.

python
def _load_credentials():
    ak, sk = "", ""
    for k, v in os.environ.items():
        u = k.upper()
        if not (u.startswith("HUAWEI") or u.startswith("HW") or u.startswith("HWC")):
            continue

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill declares shell and environment-variable dependent behavior but does not define any explicit tool scope such as allowed-tools or permissions. In an agent setting, this can cause overbroad execution authority, making it easier for the skill to invoke shell commands or access sensitive environment data beyond what is necessary for read-only ECS queries.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation instructs users to download and immediately execute a remote shell installer via bash without any integrity verification, signature check, pinning, or explicit trust warning. If the download source, transport, hosting bucket, or script content is compromised, this leads directly to arbitrary code execution on the user's machine.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents all acceptance criteria in Chinese and does not indicate that the language choice is optional, user-selectable, or required for a region-specific use case. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The guide instructs users to place long-lived Access Key and Secret Key values directly on the command line and in environment variables without warning that these secrets may be exposed through shell history, process inspection, terminal logging, CI logs, or persisted CLI configuration. In the context of a cloud ECS administration skill, compromised AK/SK credentials could let an attacker enumerate, modify, or destroy cloud resources depending on the account's permissions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script's description, help text, and user-visible messages are written only in Chinese, which imposes a fixed language choice on users. The file does not indicate that the tool is intentionally region- or language-specific, nor does it provide any opt-in or alternative locale handling.

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 · huawei_cloud_ecs_detail_query.py (reported line 70)May include surrounding context.

python
def _run_hcli(args, timeout=30):
    try:
        result = subprocess.run(["hcloud"] + args, capture_output=True, text=True, timeout=timeout)
        raw = result.stdout.strip()
        brace_start = raw.find("{")
        brace_end = raw.rfind("}")

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents all user-facing content exclusively in Chinese, which can constitute a language/locale policy violation when no user opt-in or justification is provided. The policy explicitly allows locale constraints only when documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This JSON manifest contains multiple natural-language descriptions entirely in Chinese, but there is no indication that the skill is region-specific or that users can choose their preferred language. For a general skill file, forcing a single language in descriptions can violate language/locale policy expectations and reduce accessibility for users who did not opt in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents all user-facing instructions exclusively in Chinese, which imposes a specific language on users without indicating any opt-in or alternative locale. The policy for natural-language violations applies to all file types and specifically includes forced language or locale choices.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file forces a specific language for all instructions without indicating that this is a region-specific or opt-in localization choice. Under the policy, natural-language content should not impose a language or locale without user choice unless the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code scans environment variables for AK/SK-style credentials and uses them to authenticate cloud API requests. Although credential use is functionally necessary, there is no explicit disclosure in the code comments, help text, or printed output that the tool will read sensitive environment variables.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file’s natural-language content is entirely in Chinese, including headings and usage explanations, and there is no indication that users may choose another language. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale/language policy issue.

Content

No source excerpt is available for this finding.