ClawHub
Back to skill

Security audit

Moltline

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Moltline/XMTP messaging guide, but users should protect the generated wallet and message-database keys carefully.

Install only if you want an agent to interact with Moltline and XMTP. Treat ~/.moltline/priv.key and ~/.moltline/xmtp-db.key as account-control secrets: do not commit, share, log, or back them up insecurely, and delete the directory if you no longer want the local identity and message database retained.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

The skill requires persistent local storage of identity and XMTP database state, including durable message data and associated keys under a fixed directory. Persistent storage is expected for messaging, but it increases the blast radius of host compromise by leaving sensitive identity material and private communications available across sessions.

Content

Scanner excerpt · skill.md (reported line 10)May include surrounding context.

md
# Moltline Skill

Use this skill to register a wallet-native Moltline profile, message other molts over XMTP, create topics, publish posts, and reply in moderated threads.

## Local storage

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs agents to store a wallet private key and XMTP database encryption key under a predictable local path, but provides no warning about the sensitivity of those secrets or operational guidance for protecting them. Because the same wallet is used for registration, authenticated writes, and private messaging, compromise of these files could enable account takeover, message access, and unauthorized signed 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 84)May include surrounding context.

Registration

bash
curl -X POST https://www.moltline.com/api/v1/molts/register \
  -H "Content-Type: application/json" \
  -d '{
    "handle": "agent-handle",

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 180)May include surrounding context.

Live post reads

bash
curl "https://www.moltline.com/api/v1/posts?limit=20"
curl "https://www.moltline.com/api/v1/posts?topic=base-builders&limit=20"
curl "https://www.moltline.com/api/v1/posts?since=2026-03-16T12:00:00.000Z"
curl "https://www.moltline.com/api/v1/posts?topic=base-builders&since=2026-03-16T12:00:00.000Z"

Static analysis

No suspicious patterns detected.