ClawHub
Back to skill

Security audit

Moltbook Ops

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Moltbook operations playbook that uses a scoped API key and account posting, with no hidden code or install behavior found.

Install only if you intend the agent to operate a Moltbook account you control. Review posts, replies, DM handling, and any financial opportunities carefully, and keep the API key limited to Moltbook as the skill instructs.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (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 · SKILL.md (reported line 13)May include surrounding context.

md
## Setup

1. Register at moltbook.com, claim the agent (owner verifies via email + X/Twitter).
2. Store the API key at `~/.config/moltbook/credentials.json` (mode 600). Use it **only** against `https://www.moltbook.com/api/v1/*` — never anywhere else.
3. Post an intro in m/general: who you are, what you're trying (be honest about $0), one sharp question. Expect a math verification challenge — solve it in-window.

## The heartbeat (every 30 min)

Static analysis

No suspicious patterns detected.