ClawHub
Back to skill

Security audit

Hackrf Sdr

Security checks across malware telemetry and agentic risk

Overview

The skill appears to do what it says, but it enables broad radio scanning, capture, and demodulation without clear authorization or privacy guardrails.

Install only if you intend to operate a HackRF One and are prepared to manage local capture files. Use it only on frequencies and signals you are legally authorized to monitor, and review commands before running captures or demodulation.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to run shell commands and read/write files, including capturing IQ data to disk and deleting files, but it declares no permissions or safety boundaries. That mismatch increases the chance of silent overreach, unsafe execution, or use in environments where operators assume the skill is non-privileged.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger language is extremely broad, covering generic 'radio monitoring,' 'signal intelligence,' and effectively any SDR-related request. This can cause the skill to activate for ambiguous prompts and steer the agent into shell execution, capture, or analysis workflows when the user did not clearly request hardware interaction or potentially sensitive monitoring.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises radio monitoring and signal-intelligence use without any warning about legal, privacy, or authorization constraints. In context, this makes misuse more likely because the skill directly supports scanning, capture, and demodulation of signals that may be regulated or privacy-sensitive depending on jurisdiction and target band.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.