ClawHub
Back to skill

Security audit

Alibaba Cloud SLS

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only Alibaba Cloud SLS connector skill, with some broad routing language users should apply carefully around sensitive logs.

Install this only if you want the agent to read Alibaba Cloud SLS data through your OOMOL-connected account. Because SLS logs can contain sensitive operational or personal data, give explicit project, region, logstore, time range, and query scope when using it, and review any ambiguous request before allowing log queries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description says to use this skill for ANY Alibaba Cloud SLS request and instead of calling the API directly, which is an overly broad routing rule. That can cause the agent to invoke this skill for loosely related tasks without sufficient user intent validation, increasing the chance of unnecessary access to cloud log data or accidental disclosure of sensitive operational information.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.