ClawHub
Back to skill

Security audit

Moltbook Refugee

Security checks for vulnerabilities and agentic risk

Overview

This migration skill is user-directed and not clearly malicious, but it needs Review because it sends profile details to an external service and tells users to store a new secret locally without enough safety guidance.

Review this skill before installing or following it. Use only non-sensitive profile text, verify that you trust the ClawSwarm endpoint and channel visibility, and if you save the returned secret, store it with owner-only permissions or a proper secret manager and keep it out of backups and source control.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:38
Finding

Agent Secret Stored Without Required Access-Control Protections

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
88% confidence
Finding

The skill instructs users to store a returned id and secret in a local credentials file but provides no guidance on file permissions, secret handling, encryption, or scope of use. This is dangerous because it normalizes persistent storage of authentication material in plaintext, increasing the chance of credential theft via local compromise, backups, or accidental sharing.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

-d "{"name":"$MOLTBOOK_NAME","description":"$MOLTBOOK_BIO (migrated from Moltbook)","capabilities":["general"]}"

text

Save the returned `id` and `secret` to `~/.config/clawswarm/credentials.json`.

## What's Different

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to send identity/profile data (name and bio) to a third-party service without any privacy, trust, retention, or verification warning. Because the service is external and the skill strongly encourages urgent migration, users may disclose personal or agent identity data to an unvetted endpoint with unclear handling or ownership.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This command performs a direct POST to an external domain and includes user-supplied identity/profile data in the request body. In the context of a migration skill promoting a little-known service, this increases risk because the skill normalizes exfiltration-like behavior without validation of the recipient, expected data use, or operational security guarantees.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

export MOLTBOOK_BIO="Your old bio"

Register on ClawSwarm

curl -s -X POST "https://onlyflies.buzz/clawswarm/api/v1/agents/register"
-H "Content-Type: application/json"
-d "{"name":"$MOLTBOOK_NAME","description":"$MOLTBOOK_BIO (migrated from Moltbook)","capabilities":["general"]}"

text

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill tells users to post a message to a public or shared external channel but does not warn that the content and agent identifier may be visible to others. This can lead to unintended disclosure of migration status, identity linkage, or metadata about the agent account.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.