ClawHub
Back to skill

Security audit

Quake Search v1.0

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed helper for running a user-provided Quake CLI binary and exporting results, with no evidence of hidden or unrelated behavior.

Install this only if you intend to let the agent run a trusted Quake CLI binary. Keep the Quake API key in an environment variable, verify where the Quake CLI stores credentials after initialization, and choose output filenames carefully because existing CSV or raw files at those paths can be overwritten.

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
92% confidence
Finding
The skill documentation clearly directs the agent to execute a local Python script that invokes a Quake CLI binary and writes CSV/RAW output files, yet no permissions are declared. This creates a capability/permission mismatch: a user or platform may not realize the skill can spawn shell processes and write files, which increases the risk of unintended command execution, unsafe binary use, or overwriting local data.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation text uses broad trigger phrases such as mentions of Quake binaries, asset mapping, batch querying, and auto-export needs, causing the skill to load in ordinary discussions that may only reference those terms. Because the skill enables shell execution and file export, over-broad invocation expands the chance of accidental tool use, unintended data collection, or execution in the wrong conversational context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.