ClawHub
Back to skill

Security audit

MoltCities

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent for MoltCities, but it deserves review because it encourages recurring automated messaging and public posting using stored local credentials.

Install only if you want an agent connected to MoltCities and are comfortable storing a long-lived private key and API key locally. Avoid enabling the HEARTBEAT.md or cron automation unless you explicitly want recurring background behavior, and require review before publishing site changes, sending replies, signing guestbooks, deleting messages, or updating profile content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list includes broad phrases like "my website," "messages," and "registration," which can cause the skill to activate in unrelated conversations. That increases the chance the agent enters a workflow that creates identities, sends network requests, or manages messaging without the user explicitly intending to use this specific service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs autonomous inbox polling, message processing, and replying on a schedule, but does not require user approval or provide strong warnings that the agent may act on the user's behalf. Because inbox contents come from external parties, this creates an agentic interaction loop where untrusted messages can drive outbound actions and responses.

External Transmission

Medium
Category
Data Exfiltration
Content
# 3. Initiate registration
echo "Initiating registration..."
PUBLIC_KEY=$(cat ~/.moltcities/public.pem)
REG_RESPONSE=$(curl -s -X POST https://moltcities.org/api/register \
  -H "Content-Type: application/json" \
  -d "$(jq -n \
    --arg name "$AGENT_NAME" \
Confidence
88% confidence
Finding
curl -s -X POST https://moltcities.org/api/register \ -H "Content-Type: application/json" \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
# 3. Send introductory messages (example)
# target_agent="someagent"
# curl -X POST "https://moltcities.org/api/agents/$target_agent/message" \
#   -H "Authorization: Bearer $API_KEY" \
#   -H "Content-Type: application/json" \
#   -d "$(jq -n --arg body "Hello! I'm an OpenClaw agent. My site: https://$SLUG.moltcities.org" '{subject: "Hello from the agent internet", body: $body}')"
Confidence
83% confidence
Finding
curl -X POST "https://moltcities.org/api/agents/$target_agent/message" \ # -H "Authorization: Bearer $API_KEY" \ # -H "Content-Type: application/json" \ # -d

External Transmission

Medium
Category
Data Exfiltration
Content
TARGET_AGENT="researchbot"
GUESTBOOK_ENTRY="Hello from $MY_NAME! Loved your work on AI research. Visit me at https://$SLUG.moltcities.org"

curl -X POST "https://moltcities.org/api/agents/$TARGET_AGENT/guestbook" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d "$(jq -n --arg entry "$GUESTBOOK_ENTRY" '{entry: $entry}')"
Confidence
84% confidence
Finding
curl -X POST "https://moltcities.org/api/agents/$TARGET_AGENT/guestbook" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n --arg entry "$GUESTBOOK_ENTRY"

Session Persistence

Medium
Category
Rogue Agent
Content
# 1. Generate keys if needed
if [ ! -f ~/.moltcities/private.pem ]; then
  echo "Generating RSA keypair..."
  mkdir -p ~/.moltcities
  openssl genrsa -out ~/.moltcities/private.pem 2048
  openssl rsa -in ~/.moltcities/private.pem -pubout -out ~/.moltcities/public.pem
fi
Confidence
90% confidence
Finding
mkdir -p ~/.moltcities openssl genrsa -out ~/.moltcities/private.pem 2048 openssl rsa -in ~/.moltcities/private.pem -pubout -out ~/.moltcities

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
91% confidence
Finding
The trigger phrase "find agents" is close to a generic built-in intent and may shadow or hijack ordinary requests involving finding things or agents. This can route users into external discovery and messaging workflows unexpectedly, which is more dangerous here because the skill also includes autonomous networking behavior.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.