ClawHub
Back to skill

Security audit

Qdrant Cloud

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Qdrant Cloud connector that can read and write Qdrant data through OOMOL, with write actions explicitly labeled and requiring confirmation.

Before installing, understand that this skill can access and modify data in the Qdrant Cloud account connected to OOMOL. Read-only actions may be run directly, while collection creation and point upserts should only proceed after you confirm the exact target and payload.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description says to use this skill for any Qdrant Cloud request and whenever a task involves Qdrant Cloud, which can cause over-selection of the skill based on broad keyword matching rather than explicit user intent. In a skill that includes write-capable actions such as collection creation and point upserts, overly broad invocation increases the chance the agent routes tasks here unnecessarily and reaches state-changing paths.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The skill text instructs the agent to use this skill instead of calling the API directly for any Qdrant Cloud task, removing flexibility and discouraging user-visible choice or safer alternatives. While not directly malicious, this kind of forced routing can bypass more context-appropriate handling and increases reliance on a write-capable connector whenever Qdrant is mentioned.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.