ClawHub
Back to skill

Security audit

Instagram Downloader

Security checks across malware telemetry and agentic risk

Overview

The skill appears intended for Instagram data access, but it asks users to provide reusable Instagram session credentials without clear safety boundaries.

Install only if you understand that Instagram cookie values are account credentials. Use it only with your own or explicitly authorized accounts, avoid pasting raw cookies into chat when possible, keep credential files local, and revoke or refresh the Instagram session if you suspect exposure.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs the agent to request and use Instagram authentication material, including a cookie file and manual session-related values, but provides no warning that these credentials are highly sensitive and can enable account access. In this context, collecting session cookies is privacy- and security-sensitive because the agent is normalizing handling of reusable auth tokens that could expose private content or permit account misuse if mishandled.

Ssd 3

Medium
Confidence
90% confidence
Finding
The skill directs the agent to collect a cookie file path and even instructs users how to extract sessionid and csrftoken for authenticated scraping. This is dangerous because it operationalizes the handling of account authentication artifacts, increasing the chance of credential exposure, unauthorized access to private content, or unsafe reuse of session data outside the browser.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.