Qverisai 1.0.1

• Outcome: Review
• Latest audit: May 28, 2026 at 8:53 AM UTC
• Version:
  1.0.0

Overview

This looks like a legitimate QVeris connector, but it can automatically send broad user requests into remote dynamic tool execution, so users should review the trust boundary before installing.

Install only if you trust QVeris as a broad remote-tool gateway. Use a revocable, least-privilege API key, avoid sending secrets or sensitive health, finance, account, or private business data, and configure your agent to confirm the selected tool and parameters before execution where possible.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The README explicitly promotes dynamic discovery and execution of external tools via the QVeris API but does not clearly warn that prompts and parameters may be transmitted off-platform. In an agent context, this can cause users to unknowingly send sensitive data to third-party services, making the omission security-relevant rather than merely a documentation issue.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: Saying OpenClaw will 'automatically use this skill' for common request types without warning about external API invocation obscures an important trust boundary. In practice, ordinary user queries about weather, finance, search, or similar topics could silently trigger outbound requests, potentially exposing confidential prompts or contextual data to third parties.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill is configured with auto-invocation enabled while advertising an extremely broad capability surface spanning many common user intents, which can cause it to trigger in situations far beyond narrowly intended use. Because the skill performs dynamic external tool discovery and execution against a third-party API, over-broad triggering increases the chance of unintended data disclosure, unnecessary external requests, and execution of unvetted remote tool actions in response to ordinary prompts.

VirusTotal

66/66 vendors flagged this skill as clean.