Bounty Hunter Pro

• Outcome: Review
• Latest audit: May 29, 2026 at 9:22 PM UTC
• Version:
  1.0.0

Overview

This is a legitimate-looking bug-bounty scanning skill, but it needs review because it can drive live and recurring scans with weak scope controls.

Review before installing or using. Only run it on programs where you have explicit authorization, replace the sample authorization check with strict hostname and subdomain-boundary validation, verify any external scanner binaries yourself, avoid sending raw secrets to cloud models or shared alert channels unless approved, and do not enable the cron schedule unless recurring scans are intentional.

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
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Intent-Code Divergence

High

• Confidence: 99% confidence
• Finding: The documented authorization check is flawed because `target.endswith(auth)` will treat unrelated domains like `badexample.com` as authorized when `example.com` is on the allowlist. In a skill explicitly designed for autonomous vulnerability scanning, this creates a real scope-bypass that can lead to unauthorized scanning of third-party infrastructure.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The invocation text is broad enough that an agent could start an active bounty scan from a simple prompt without strong confirmation, exclusions, or a mandatory preflight step. Because this skill performs network enumeration and vulnerability scanning, ambiguous triggering increases the chance of unintended or unauthorized execution.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill advertises autonomous scanning, analysis, and report generation but does not prominently warn that it will perform live network activity and write artifacts to disk. In a security-scanning context, lack of explicit operational disclosure is dangerous because users or agents may trigger intrusive actions and persistent storage without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.