summarizer

Security checks across malware telemetry and agentic risk

Overview

This YouTube summarizer does what it advertises, but it stores transcripts locally and sends transcript content to external services.

Install only if you are comfortable with full YouTube transcripts being saved locally, sent to SkillBoss for summarization, and attached to Telegram in Telegram chats. For safer use, inspect or pin the external MCP dependency, avoid private or sensitive videos, and periodically delete saved transcript files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README explicitly says full transcripts are saved to local files, but it does not warn users about persistence, retention, disk exposure, or the possibility that transcripts may contain sensitive spoken content. In an agent environment, silent local storage can create privacy and compliance risk because users may assume the action is ephemeral while the skill leaves recoverable artifacts on disk.

Missing User Warnings

High
Confidence
97% confidence
Finding
The documentation states that summary generation is routed through SkillBoss API Hub, but it does not clearly warn that transcript content and associated metadata are transmitted to an external service. This is dangerous because users may share private or copyrighted video content without realizing the data leaves the local environment and may be subject to third-party logging, retention, or policy controls.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends the full transcript text plus video metadata to a third-party API for summarization, but the instructions do not require obtaining explicit user consent or warning that content leaves the local environment. Even if the transcript is user-requested, it may contain sensitive or copyrighted material, and silent transfer to an external service creates privacy, compliance, and data-handling risk.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to save full transcripts to a persistent local file path without notifying the user that requested content will be stored on disk. Persistent storage increases exposure to later unauthorized access, accidental reuse, or retention beyond user expectations.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill directs the agent to send transcript files to Telegram, an external messaging platform, without an explicit warning or confirmation step. This can expose full video content and metadata to third-party infrastructure and potentially to the wrong recipient if the chat target is misconfigured.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def generate_summary(transcript_text: str, title: str, author: str) -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
Confidence
90% confidence
Finding
requests.post( "https://

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def generate_summary(transcript_text: str, title: str, author: str) -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
Confidence
90% confidence
Finding
requests.post( "https://api.heybossai.com/v1/pilot", headers={ "Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json" },

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal