youtube-channel-api-skill

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 4:00 AM UTC
• Version: 1.0.0

Overview

This skill is a coherent YouTube channel search helper that sends search parameters to BrowserAct using the user's API key, with no evidence of hidden persistence or unrelated behavior.

Install this only if you are comfortable sending YouTube search keywords and filters to BrowserAct under your BrowserAct account. Avoid using sensitive competitive or private research terms unless that third-party processing is acceptable to you, and verify the API key is scoped and managed appropriately.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence
• Finding: The skill invokes a Python script, relies on an environment secret, and communicates with an external API, but it does not declare any explicit tool scope or allowed tools. This weakens policy enforcement and reviewability, making it easier for an agent to use network and secret-backed execution implicitly without clear consent boundaries.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The activation text is very broad and encourages proactive use across many loosely related scenarios, which can cause the agent to invoke the skill when the user did not intend external data collection or third-party processing. In this context, unintended invocation is more dangerous because the skill sends user-supplied search terms to BrowserAct and uses an API key-backed integration.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill does not clearly warn users that their search terms and request parameters will be transmitted to an external service. This creates a privacy and consent risk, especially if users provide sensitive research topics, brand-monitoring targets, or competitive intelligence queries they may not expect to leave the local agent environment.

External Transmission

Medium

• Category: Data Exfiltration

Content

# API Configuration
TEMPLATE_ID = "82306405322792301"
API_BASE_URL = "https://api.browseract.com/v2/workflow"

def run_youtube_channel_task(api_key, keywords, upload_date="Any time"):
    headers = {"Authorization": f"Bearer {api_key}"}

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

# 1. Start Task
    print(f"Start Task", flush=True)
    try:
        res = requests.post(f"{API_BASE_URL}/run-task-by-template", json=payload, headers=headers).json()
    except Exception as e:
        print(f"Error: Connection to API failed - {e}", flush=True)
        return None

• Confidence: 80% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.