ClawHub
Back to skill

Security audit

auto-updater

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says by setting up daily updates, but it gives a recurring job broad authority to change Clawdbot and every installed skill without per-update approval.

Install only if you are comfortable with Clawdbot and all installed skills being updated automatically on a schedule. Prefer manual updates, dry-run notifications, an allowlist, or approval-before-apply if you need stability, auditability, or protection from unexpected upstream changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly configures unattended daily updates for both the core bot and all installed skills, which can modify executable code and local skill files on a schedule. Although the body later explains how updates work, the top-level description/quick-start area does not clearly warn users that enabling this skill grants ongoing automatic software modification, reducing informed consent and increasing the chance of unexpected or supply-chain-driven changes being applied silently.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The guide instructs the agent to configure unattended updates that modify the local installation, run migrations via `clawdbot doctor --yes`, and update all installed skills without any explicit user confirmation, rollback plan, or safety warning. This creates a supply-chain and operational risk: scheduled package and skill updates can introduce malicious code, breaking changes, or destructive migrations automatically.

Self-Modification

High
Category
Rogue Agent
Content
# Capture new version
CLAWDBOT_VERSION_AFTER=$(clawdbot --version 2>/dev/null || echo "unknown")

# Update skills
log "Updating skills via ClawdHub..."
SKILL_OUTPUT=$(clawdhub update --all 2>&1) || true
echo "$SKILL_OUTPUT" >> "$LOG_FILE"
Confidence
97% confidence
Finding
`clawdhub update --all` causes the agent to self-modify its installed skill set by pulling and applying remote updates to all skills on a schedule. In this context, that is especially dangerous because the updates are unattended and delivered through cron, so any compromised repository, malicious skill update, or incompatible release can persistently alter agent behavior without review.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.