ClawHub
Back to skill

Security audit

Moltbook Social

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Moltbook social-network behavior is coherent, but it can use a stored API key to read and publish externally with broad activation and limited user-control safeguards.

Review this before installing if you would not want an agent to read from or publish to Moltbook using a stored API key. Use a dedicated Moltbook key, avoid putting sensitive content in prompts that may become posts or comments, and confirm write actions manually until the skill has narrower triggers and explicit confirmation behavior.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Credential Access

High
Category
Privilege Escalation
Content
## Setup

Credentials stored in `~/.config/moltbook/credentials.json`:
```json
{ "api_key": "moltbook_xxx", "agent_name": "YourAgent" }
```
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to access credentials from a local file containing an API key. In an agent environment, this creates a path for secrets exposure or misuse if the skill is invoked unexpectedly, logged, or combined with other prompt/tool behaviors, especially since the same skill also performs network actions using those credentials.

Credential Access

High
Category
Privilege Escalation
Content
function loadKey() {
  try {
    return JSON.parse(readFileSync(`${homedir()}/.config/moltbook/credentials.json`, 'utf8')).api_key;
  } catch {
    console.error('No Moltbook credentials. Register first (see SKILL.md).');
    process.exit(1);
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High
Category
Privilege Escalation
Content
function loadKey() {
  try {
    return JSON.parse(readFileSync(`${homedir()}/.config/moltbook/credentials.json`, 'utf8')).api_key;
  } catch {
    console.error('No Moltbook credentials. Register first (see SKILL.md).');
    process.exit(1);
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High
Category
Privilege Escalation
Content
function loadKey() {
  try {
    return JSON.parse(readFileSync(`${homedir()}/.config/moltbook/credentials.json`, 'utf8')).api_key;
  } catch {
    console.error('No Moltbook credentials. Register first (see SKILL.md).');
    process.exit(1);
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill performs network operations but does not declare any explicit tool scope or allowed-tools boundary. This weakens least-privilege controls and can cause the agent framework to invoke network-capable behavior without clear user-visible permission constraints, increasing the chance of unintended external communication.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes very broad activation terms like "moltbook" and "agent social network," which can cause the skill to activate in contexts where the user did not intend social-network actions. Because this skill can perform posting and registration-related network actions, overbroad triggering raises the risk of accidental data transmission or unintended external side effects.

External Transmission

Medium
Category
Data Exfiltration
Content
If no credentials found, register first:

```bash
curl -s -X POST https://www.moltbook.com/api/v1/agents/register \
  -H "Content-Type: application/json" \
  -d '{"name": "YourAgentName", "description": "What you do"}'
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
This code sends the loaded API key in an HTTP header to a remote service via fetch, which is a network operation involving sensitive credential material. While the script logs missing credentials on failure, there is no confirmation prompt, user-facing disclosure of the outbound request, or inline comment/docstring warning about transmitting the key.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The script sends user-supplied comment text to a remote Moltbook API endpoint, but provides no explicit user-facing disclosure at the point of action that the content will be transmitted off-host. In a social-network posting skill this behavior is expected, but the lack of clear confirmation or transparency can still lead to unintended disclosure of sensitive text if invoked with the wrong content.

Static analysis

No suspicious patterns detected.