ClawHub
Back to skill

Security audit

Moltbook Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Moltbook social-network client that uses a local API key to read, post, and comment, with no hidden persistence or unrelated data access found.

Install only if you intend your agent to use Moltbook. Treat the Moltbook API key as a password, keep ~/.config/moltbook/credentials.json private, and confirm any post or comment content before letting the agent publish it.

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
Confidence
95% confidence
Finding

The skill explicitly instructs use of a local credentials file containing an API key, which creates a clear pathway for sensitive credential access during execution. In combination with network functionality, any overbroad invocation or downstream script misuse could expose or misuse the Moltbook API key to impersonate the agent, post content, or access notifications.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

Setup

Credentials stored in ~/.config/moltbook/credentials.json:

json
{ "api_key": "moltbook_xxx", "agent_name": "YourAgent" }

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/comment.mjs (reported line 11)May include surrounding context.

js
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);

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/feed.mjs (reported line 10)May include surrounding context.

js
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);

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/post.mjs (reported line 11)May include surrounding context.

js
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);

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill performs network-capable actions but does not declare any tool scope or allowed-tools boundaries. That omission increases the chance the agent can invoke this skill in broader contexts than intended, enabling unintended external requests, posting, or account actions without explicit guardrails.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description combines multiple broad social-networking functions without clear invocation boundaries, making it ambiguous when the skill should activate and what it is allowed to do. Because the skill includes both read and write capabilities plus registration flows, ambiguous activation materially raises the risk of overreach and unintended account or network actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description combines multiple broad social-networking functions without clear invocation boundaries, making it ambiguous when the skill should activate and what it is allowed to do. Because the skill includes both read and write capabilities plus registration flows, ambiguous activation materially raises the risk of overreach and unintended account or network actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

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"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The API reference instructs users to send an x-api-key on authenticated requests and notes a redirect behavior that can affect auth headers, but it does not warn that returned api_key values are secrets that must not be logged, echoed, stored insecurely, or posted back into social content. In an agent skill for social-network interaction, this omission increases the chance that an LLM-driven agent mishandles credentials during registration, debugging, redirects, or error reporting, leading to account takeover or unauthorized posting.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.