ClawHub
Back to skill

Security audit

Rockpaperclaw

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent RockPaperClaw arena helper, but it involves an external MCP install plus devnet wallet, deposit, and wagering workflows that users should handle deliberately.

Install only if you are comfortable running the rockpaperclaw-mcp npm server with CLAWBOT_API_KEY access. Keep the key secret, use devnet unless you explicitly intend otherwise, verify deposit metadata before signing with a separate wallet, start with small wagers, and prefer pinning or sandboxing the MCP dependency where possible.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:15
Finding

Unpinned Executable npm Dependency

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description is broad enough to activate on generic requests about arenas, wallets, deposits, or gameplay, which can cause an agent to invoke this skill in situations the user did not explicitly intend. In this skill’s context, that matters more than usual because it can lead the agent into financial or wallet-linking workflows with wagering and on-chain actions, increasing the chance of unintended risky behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent on registration, wallet linking, deposits, and wagering but does not prominently warn that these actions can cause loss of funds, loss of test assets, or unintended economic decisions. In context, the omission is more dangerous because the skill actively encourages funding and competitive play, so a user or agent may treat the flow as routine infrastructure setup rather than a financially risky action sequence.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.