Back to skill

Security audit

Huawei Cloud Cce Ops Report Generator

Security checks for vulnerabilities and agentic risk

Overview

This report skill needs review because it claims to be read-only but ships callable code for secret access and live cluster changes.

Do not install this with broad Huawei or Kubernetes administrator credentials as-is. Treat it as a review item until the publisher ships a report-only dispatcher with an enforced allowlist, removes undeclared mutation and Secret-data actions, confines on-call input paths, fixes TLS verification and temporary credential handling, and pins dependencies. If testing is necessary, use an isolated environment with read-only cloud and Kubernetes credentials and avoid include_raw for sensitive data.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (6)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/huawei_cloud/ops_report_generator.py:42
Finding

Arbitrary Local File Disclosure Through On-Call Report Input

Content
View full analysis
Optional[str]: if not path: return None candidate = Path(path) if not candidate.exists(): return None try: return candidate.read_text(encoding="utf-8") except OSError: return None def _extract_oncall(oncall_report_path: Optional[str], oncall_summary: Optional[str]) -> Dict[str, Any]: if oncall_summary: return { "status": "provided", "source": "inline", "summary": oncall_summary.strip(), "details": None, } if not oncall_report_path: return { "status": "missing", "source": None, "summary": "oncall-copilot report not provided", "details": None, } path = Path(oncall_report_path) if not path.exists(): return { "status": "missing", "source": str(path), "summary": "oncall-copilot report path does not exist", "details": None, } try: if path.suffix.lower() == ".json": payload = json.loads(path.read_text(encoding="utf-8")) summary = payload.get("summary") if isinstance(payload, dict) else None return { "status": "provided", "source": str(path), "summary": str(summary) if summary else "oncall-copilot JSON loaded", "details": payload, } content = path.read_text(encoding="utf-8") except (OSError, json.JSONDecodeError) as exc: return { "status": "error", "source": str(path), "summary": f"failed to read oncall-copilot report: {exc}", "details": None, } snippet = conten ...[truncated 2233 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/huawei_cloud/cce.py:3362
Finding

Predictable Temporary Files Expose Kubernetes Client Private Keys

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/huawei_cloud/network.py:681
Finding

TLS Verification Disabled for Signed Huawei Cloud Requests

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/huawei_cloud/cce.py:3342
Finding

Kubernetes API Server Certificate Verification Disabled

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
scripts/huawei_cloud/dispatcher.py:1469
Finding

Report-Only Skill Bundles Destructive and Secret-Access Actions

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:65
Finding

Unpinned Runtime Dependencies Create Supply-Chain Risk

Content
View full analysis
= 3.6 and the following packages: - `huaweicloudsdkcore` - `huaweicloudsdkcce` - `huaweicloudsdkaom` - `huaweicloudsdkhss` - `huaweicloudsdkvpc` - `huaweicloudsdkecs` - `huaweicloudsdkces` - `huaweicloudsdkevs` - `huaweicloudsdkeip` - `huaweicloudsdkelb` - `huaweicloudsdkiam` - `kubernetes` - `matplotlib` - `numpy` Install: `pip3 install huaweicloudsdkcore huaweicloudsdkcce huaweicloudsdkaom huaweicloudsdkhss huaweicloudsdkvpc huaweicloudsdkecs huaweicloudsdkces huaweicloudsdkevs huaweicloudsdkeip huaweicloudsdkelb huaweicloudsdkiam kubernetes matplotlib numpy` ``` ### Technical Analysis The documented installation command resolves many packages without exact versions, hashes, a lock file, or an explicitly trusted package index. Consequently, the effective code installed with the Skill can change over time without any change to the reviewed artifact. Python package installation can execute build backends and installation logic. A compromised upstream release, dependency takeover, index substitution, or incompatible future release could therefore execute code with the installer’s privileges. No evidence was found that these package names are intentionally malicious or typosquatted. The confirmed issue is the absence of reproducible dependency controls. ### Attack Path 1. An operator follows the documented `pip3 install` command. 2. The resolver selects the latest versions and transitive dependencies available at installation time. 3. A compromised or substituted package is downloaded because no version or hash constraint prevents it. 4. Package build or import code executes in the Skill environment. 5. The malicious dependency gains access to the process environment, including Huawei credentials available during Skill exec ...[truncated 431 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (437)

Context-Inappropriate Capability

Critical
Category
Not specified by scanner
Confidence
99% confidence
Finding

The code replaces a live Kubernetes Deployment object to roll back workloads in a cluster, which is a direct state-changing operation. In the context of a report generator, this is especially dangerous because it enables production-impacting changes under an unjustified interface, creating risk of accidental rollback, privilege abuse, or hidden destructive behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Critical
Category
Not specified by scanner
Confidence
99% confidence
Finding

The secret-listing functionality can return Kubernetes Secret contents when include_data=true, exposing sensitive material such as tokens, passwords, certificates, and API keys. This is especially dangerous in a report-generation context because secret extraction is unrelated to the stated use case and can facilitate credential theft and lateral movement.

Content

No source excerpt is available for this finding.

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL-CN.md (reported line 1)May include surrounding context.

md
---
name: ops-report-generator
description: Use this skill for Huawei Cloud CCE operations reporting that consolidates daily inspection, capacity trend, availability risk, cost optimization, and on-call context into weekly, monthly, SLA, capacity, or stability reports with both Markdown and HTML output.
---

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Cloud IAM authentication inputs, ECS lookup by IP, and security-group inspection indicate handling of sensitive account and network-security context outside the declared reporting purpose. That broadens both credential exposure risk and the amount of privileged reconnaissance possible through the skill.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal, suspicious.insecure_tls_verification

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/huawei_cloud/cce_nodepool.py:456

HTTPS certificate verification is disabled.

Warn
Code
suspicious.insecure_tls_verification
Location
scripts/huawei_cloud/network.py:781

HTTPS certificate verification is disabled.

Warn
Code
suspicious.insecure_tls_verification
Location
scripts/huawei_cloud/storage.py:416