Back to skill

Security audit

huawei-cloud-ccm-certificate-query

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because an endpoint override could send cloud authentication identifiers and signatures to an arbitrary HTTPS host.

Consider the credential exposure risk before installing. The Skillspector scan was partial: it inspected all listed components, but four local references could not be resolved, so the evidence is incomplete.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

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

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.

Error-message acceptance criteria require Chinese output without user opt-in.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The acceptance criterion explicitly requires a “Chinese hint” for export errors, imposing a specific output language. The file provides neither a user language choice nor a documented regional justification for this requirement.

Content

No source excerpt is available for this finding.

An unrestricted endpoint override sends cloud authentication material to arbitrary HTTPS hosts, beyond the stated Huawei Cloud SCM query scope.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The endpoint override accepts arbitrary hosts, and ScmClient sends an Authorization header containing the access-key identifier and signature, plus the optional security token, to that host. If an attacker influences the endpoint argument, these values reach an attacker-controlled server despite the read-only cloud-operation scope; HTTPS authenticates that chosen server but does not make it trusted. The secret key itself is not transmitted, and the signature is host-bound, limiting direct replay against Huawei Cloud.

Content

No source excerpt is available for this finding.

Markdown export rules require Chinese expiry labels without user language choice.

Low
Category
Output Handling
Confidence
96% confidence
Finding

The export rules explicitly require expiry grades to be shown using Chinese labels, regardless of the user's language. The skill provides neither a language opt-in nor a documented justification for restricting this output to Chinese.

Content

No source excerpt is available for this finding.