ClawHub
Back to skill

Security audit

Edison Autopilot Post X

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it deserves Review because it can autonomously publish AI-generated posts from a real X account and share generated/error content with external services.

Install only if you are comfortable giving this script credentials that can post from your X account. Start with --dry-run, use a test or low-risk account, leave SCAN_DIR unset unless it contains non-sensitive material, keep Telegram optional, use dedicated least-privilege API keys where possible, and remove the cron entry when you no longer want autonomous posting.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tainted flow: 'text' from requests.post (line 187, network input) → requests.post (network output)

Medium
Category
Data Flow
Content
for _ in range(3):
        if len(text) <= 280:
            break
        resp = requests.post(
            "https://api.openai.com/v1/chat/completions",
            headers={"Authorization": f"Bearer {OPENAI_KEY}", "Content-Type": "application/json"},
            json={
Confidence
82% confidence
Finding
resp = requests.post( "https://api.openai.com/v1/chat/completions", headers={"Authorization": f"Bearer {OPENAI_KEY}", "Content-Type": "application/json"}, j

Tainted flow: 'msg' from requests.post (line 231, network input) → requests.post (network output)

Medium
Category
Data Flow
Content
f"Error: {error_msg}"
        )
    try:
        requests.post(
            f"https://api.telegram.org/bot{TG_BOT_TOKEN}/sendMessage",
            data={"chat_id": TG_CHAT_ID, "text": msg, "disable_web_page_preview": True},
            timeout=10,
Confidence
91% confidence
Finding
requests.post( f"https://api.telegram.org/bot{TG_BOT_TOKEN}/sendMessage", data={"chat_id": TG_CHAT_ID, "text": msg, "disable_web_page_preview": True}, timeo

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly promotes a hands-free system that generates and posts content to a real X account, but it does not prominently warn users about the operational and reputational consequences of running the non-dry-run path. Because the setup instructions normalize immediate real posting and cron-based automation, a user could unintentionally publish unwanted, policy-violating, or brand-damaging content to a live account.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly promotes autonomous posting to X and Telegram notifications, but it does not clearly warn users that it will perform external actions on their behalf or transmit generated content to third-party services on a schedule. In agent or skill ecosystems, this is risky because users may enable it without fully understanding the scope of unattended account activity and outbound data flows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.