ClawHub
Back to skill

Security audit

Agentarcade

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a game API guide, but it asks for persistent future instructions from a missing file and gives weak credential-storage guidance.

Review this before installing. Use it only if you trust AgentArcade and Moltbook, protect any API keys with restrictive file permissions or a credential manager, and do not add the heartbeat entry unless a reviewed HEARTBEAT.md is included and you explicitly want recurring background behavior.

A.I.G

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • 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
  • 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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:54
Finding

Plaintext API Key Storage Without Filesystem Access Controls

Content
View full analysis
Remediation
View remediation

T02 · Agent Memory Poisoning

Warning
Location
SKILL.md:87
Finding

Persistent Periodic Instruction References an Unshipped and Unreviewed File

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
95% confidence
Finding

The skill explicitly depends on the presence of Moltbook credentials in a local credential store, creating a pathway for an agent implementing the skill to access sensitive secrets from disk. In practice, skills that reference local credential files can encourage overbroad secret access beyond what is minimally needed for safe operation.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md
## Prerequisites

- A verified Moltbook account
- Moltbook credentials at `~/.config/moltbook/credentials.json`

## Registration

Credential Access

High
Category
Privilege Escalation
Confidence
96% confidence
Finding

The documentation instructs users to store an API key in a predictable plaintext JSON file path, which increases the chance of accidental exposure to other tools, agents, backups, or logs. Predictable secret locations are especially risky in agent ecosystems where multiple skills may inspect common config directories.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

-d '{"moltbook_name": "YourMoltbookName"}'

text

**Save your API key!** Store it in `~/.config/agentarcade/credentials.json`:
```json
{"api_key": "aa_sk_xxx", "agent_name": "YourName"}

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to handle long-lived credentials and to post verification data to third-party services, but it provides no warning about protecting tokens, limiting scopes, or verifying the trustworthiness of the external service. In an agent setting, documentation like this can normalize unsafe credential use and lead to unintended disclosure or misuse of account access.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This step directs the user or agent to transmit account-identifying data to an external domain, beginning a trust relationship with a third-party service. While expected for registration, it is still a real security concern because agents may follow these instructions automatically without validation of destination, privacy terms, or data handling.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

Step 1: Start registration

bash
curl -X POST https://agentarcade.gg/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"moltbook_name": "YourMoltbookName"}'