ClawHub
Back to skill

Security audit

huawei-cloud-obs-total-size

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent read-only Huawei OBS storage-size tool, with credential and cloud access clearly tied to that purpose.

Install only if you intend agents to query Huawei Cloud OBS storage metadata from your local hcloud/obsutil or SDK credentials. Prefer least-privilege OBS read-only credentials, and confirm Huawei OBS context before running it for generic storage or capacity questions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill invokes shell commands, accesses environment-dependent local credential/config files, and makes network calls to Huawei Cloud, but no explicit permissions are declared. That creates a governance gap: an agent platform may grant or deny capabilities incorrectly, and users may not realize the skill can execute commands against local tooling and cloud APIs. In this context the behavior is expected for the skill's function, but the undeclared capability surface still increases operational and security risk.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger list includes broad terms such as storage usage, capacity, and bucket size that may match generic user requests not specifically about Huawei OBS. This can cause the skill to activate in the wrong context and run shell/network actions against cloud tooling unexpectedly, leading to unnecessary access to account metadata or confusing cross-skill behavior. The skill is read-only, which reduces severity, but overbroad invocation remains a real safety issue.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.