ClawHub
Back to skill

Security audit

ClawVille

Security checks across malware telemetry and agentic risk

Overview

This is a coherent ClawVille game skill, with some ordinary but important credential and automation precautions for users.

Install only if you want an agent to actively play ClawVille. Store CLAWVILLE_API_KEY in an environment variable or secret manager rather than TOOLS.md, avoid running registration in shared terminals or CI logs, provide a non-sensitive agent name instead of relying on hostname defaults, and review any cron schedule so the agent does not keep making game actions longer or more often than intended.

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 (6)

Missing User Warnings

Low
Confidence
92% confidence
Finding
The README instructs users to place a live API credential into an environment variable for an external service without any guidance on secret handling, storage, rotation, or avoiding accidental disclosure. While this is common practice, the omission increases the chance that users will expose the key through shell history, logs, screenshots, or committing setup snippets into version control.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly tells users to place a live API key in TOOLS.md or config, and the example shows the secret in a human-readable form without any warning against plaintext storage, logging, syncing, or repository exposure. In agent environments, TOOLS.md and similar files may be readable by other tools, included in prompts, committed to source control, or surfaced in diagnostics, which can lead to credential theft and unauthorized use of the ClawVille account.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script sends host-derived and user-supplied values (the default hostname, agent name, and description) to an external service during registration without clearly informing the operator what exact data leaves the system. This can expose identifying infrastructure details or sensitive user-provided content, especially because the default behavior silently uses the local hostname when no name is supplied.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The script prints the returned API key directly to stdout and instructs the user to copy it into files and shell commands, which increases the chance of secret leakage through terminal logs, shell history, screen recording, CI logs, or shared sessions. Exposing credentials in plaintext can enable unauthorized use of the remote account if the output is observed or stored.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill enables automated job execution by default, which causes the agent to take external actions without an explicit opt-in or a prominent warning to the user. In a game/economy context tied to an API key and scheduled check-ins, this can lead to unintended account activity, consumption of rate limits or in-game resources, and behavior the owner did not knowingly authorize.

External Transmission

Medium
Category
Data Exfiltration
Content
echo "🏙️ Registering $NAME with ClawVille..."

RESPONSE=$(curl -s -X POST "$API_URL/register" \
  -H "Content-Type: application/json" \
  -d "{\"name\": \"$NAME\", \"description\": \"$DESC\"}")
Confidence
89% confidence
Finding
curl -s -X POST "$API_URL/register" \ -H "Content-Type: application/json" \ -d

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.